© 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. 14089
    Prev
    Next
    INDEX
    Explanations

    references to hands or hand-related actions

    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
    137
    +0.16
    0.5%
    556
    +0.14
    0.4%
    378
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    747
    +0.16
    0.03
    556
    +0.14
    0.03
    506
    +0.13
    0.03
    Negative Logits
    BIL
    -1.20
    hya
    -1.11
    è¦ļéĨĴ
    -1.08
     Flavoring
    -1.07
    anut
    -1.06
    natureconservancy
    -1.05
     Cosponsors
    -1.03
    ashtra
    -1.02
    oult
    -1.01
    BAT
    -1.00
    POSITIVE LOGITS
     strokes
    0.95
     circles
    0.94
     flank
    0.91
     counsel
    0.89
    hander
    0.88
     Cullen
    0.86
     populism
    0.86
     Lug
    0.86
     slic
    0.86
     eject
    0.85
    Activations Density 0.446%

    No Known Activations