© 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. 5287
    Prev
    Next
    INDEX
    Explanations

    calls to action and exclamatory statements

    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
    640
    +0.17
    0.6%
    6
    +0.11
    0.4%
    173
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.17
    0.11
    640
    +0.11
    0.09
    679
    +0.11
    0.09
    Negative Logits
    yrus
    -1.06
     destro
    -0.92
    idon
    -0.91
    oun
    -0.88
    Ö¼
    -0.88
    pex
    -0.86
    undai
    -0.85
    stem
    -0.85
     disputed
    -0.82
    ©¶æ
    -0.79
    POSITIVE LOGITS
     :)
    1.32
     ;)
    1.22
    @#&
    1.21
     :-)
    1.21
     ðŁĻĤ
    1.09
    ?!
    1.08
    #$
    1.07
     Especially
    1.07
     Come
    1.03
    NOW
    1.03
    Activations Density 1.112%

    No Known Activations