© 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. 5339
    Prev
    Next
    INDEX
    Explanations

    exclamations or interjections

    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
    475
    +0.04
    0.4%
    135
    +0.04
    0.4%
    488
    +0.03
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.04
    0.01
    284
    +0.04
    0.01
    456
    +0.03
    0.01
    Negative Logits
     bidding
    -0.32
     promotional
    -0.31
     ticket
    -0.31
     PvP
    -0.30
     camping
    -0.29
     taped
    -0.29
     yourselves
    -0.28
     tapes
    -0.28
     site
    -0.28
     Edit
    -0.28
    POSITIVE LOGITS
    vg
    0.42
    pas
    0.41
    utterstock
    0.37
    imar
    0.35
    ulp
    0.34
    anches
    0.34
    ierre
    0.34
    owa
    0.33
    anes
    0.33
    iren
    0.33
    Activations Density 0.031%

    No Known Activations