© 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. 40509
    Prev
    Next
    INDEX
    Explanations

    references to specific laws or programs, particularly related to security and defense

    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
    7
    +0.13
    0.7%
    231
    +0.10
    0.5%
    253
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.27
    326
    +0.10
    0.24
    709
    +0.09
    0.14
    Negative Logits
    leted
    -0.80
    urden
    -0.73
    hops
    -0.72
    uren
    -0.71
    cember
    -0.69
    %]
    -0.67
    assetsadobe
    -0.67
    ĺ
    -0.66
    bling
    -0.66
    bern
    -0.65
    POSITIVE LOGITS
     Duty
    0.62
     Pilgrim
    0.61
    ously
    0.60
     Sentinel
    0.57
     Riders
    0.57
     Vest
    0.56
     Prayer
    0.56
    azines
    0.55
     Hearts
    0.55
    Deal
    0.54
    Activations Density 8.609%

    No Known Activations