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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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 Local
    9. 6-RES_SCL-AJT
    11. 40498
    Prev
    Next
    INDEX
    Explanations

    video clips or footage in text data

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.16
    0.8%
    187
    +0.14
    0.7%
    241
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.16
    0.20
    288
    +0.14
    0.18
    241
    +0.09
    0.08
    Negative Logits
    ichick
    -0.91
    ccording
    -0.75
    velt
    -0.74
    iott
    -0.72
    ksh
    -0.71
    chwitz
    -0.60
    abad
    -0.60
    ignt
    -0.60
    gregation
    -0.59
    ADRA
    -0.59
    POSITIVE LOGITS
     clips
    0.98
     clip
    0.98
    clips
    0.90
    clip
    0.85
     Clip
    0.82
    boards
    0.78
     coupons
    0.73
    utic
    0.71
     reel
    0.71
    aneous
    0.68
    Activations Density 6.406%

    No Known Activations