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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7754
    Prev
    Next
    INDEX
    Explanations

    information related to rules, regulations, and instructions presented in a structured format

    oai_token-act-pair · gpt-3.5-turbo
    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
    160
    +0.23
    0.9%
    274
    +0.14
    0.5%
    99
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.23
    0.08
    160
    +0.14
    0.09
    693
    +0.14
    0.07
    Negative Logits
    awaru
    -1.06
    rolet
    -1.00
    etz
    -0.95
    ooters
    -0.91
    lehem
    -0.87
    gerald
    -0.87
    otle
    -0.87
    uated
    -0.86
    anasia
    -0.85
    urized
    -0.81
    POSITIVE LOGITS
    nd
    2.16
    ND
    1.24
    147
    1.16
    ½
    1.14
    160
    1.10
     thirds
    1.09
    133
    1.08
     Corinthians
    1.07
    155
    1.05
    187
    1.04
    Activations Density 1.795%

    No Known Activations