© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 14119
    Prev
    Next
    INDEX
    Explanations

    mentions of social or political issues related to community well-being and activism

    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
    393
    +0.34
    1.5%
    120
    +0.13
    0.6%
    659
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.34
    0.13
    120
    +0.13
    0.10
    484
    +0.12
    0.10
    Negative Logits
    GMT
    -0.93
    oret
    -0.75
    ãĤ¤
    -0.73
    xt
    -0.73
    éŃĶ
    -0.70
    :(
    -0.70
     Powered
    -0.69
    Character
    -0.68
    going
    -0.67
    igmatic
    -0.66
    POSITIVE LOGITS
     assorted
    0.92
    friends
    0.86
     vice
    0.83
     consequently
    0.82
     associates
    0.81
     others
    0.81
    doms
    0.80
    gans
    0.79
     possibly
    0.78
     allies
    0.77
    Activations Density 1.585%

    No Known Activations