© 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. 14217
    Prev
    Next
    INDEX
    Explanations

    data related to military equipment and technical specifications

    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
    339
    +0.16
    0.6%
    326
    +0.14
    0.5%
    167
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.16
    0.18
    288
    +0.14
    0.16
    683
    +0.12
    0.09
    Negative Logits
    osc
    -0.98
    shire
    -0.92
    coe
    -0.90
    ovie
    -0.90
    asio
    -0.89
    utenberg
    -0.83
    cycl
    -0.83
    helle
    -0.82
    roads
    -0.81
    phrine
    -0.81
    POSITIVE LOGITS
    576
    1.02
    IELD
    0.98
    EEP
    0.95
    ::::::::
    0.93
    kHz
    0.92
    hof
    0.90
     Shades
    0.89
    knife
    0.89
    hips
    0.86
    lift
    0.86
    Activations Density 4.452%

    No Known Activations