© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 5947
    Prev
    Next
    INDEX
    Explanations

    words related to educational or academic content, including topics like theology, energy conversion, grammar and linguistic terminology, and historical events

    oai_token-act-pair · gpt-3.5-turbo

    words related to academic or competitive stages such as "Semifinalists" or elements of structured levels particularly in educational or formal contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    715
    +0.13
    0.5%
    444
    +0.13
    0.5%
    642
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.06
    326
    +0.13
    0.05
    444
    +0.13
    0.03
    Negative Logits
    leneck
    -0.83
    ards
    -0.82
     Strauss
    -0.80
    fits
    -0.79
    landish
    -0.77
     Alonso
    -0.76
    gets
    -0.76
     Nobel
    -0.74
    wagon
    -0.74
     Varg
    -0.73
    POSITIVE LOGITS
    blance
    1.25
    BLE
    1.08
    phis
    1.05
    ILY
    1.02
    antics
    1.01
    porary
    1.00
    iple
    0.98
    inished
    0.98
    inar
    0.95
    pered
    0.92
    Activations Density 0.597%

    No Known Activations