© 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. 45848
    Prev
    Next
    INDEX
    Explanations

    words related to legal and political contexts, especially related to individuals and their actions

    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
    420
    +0.19
    0.9%
    232
    +0.11
    0.5%
    97
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.19
    0.18
    232
    +0.11
    0.07
    420
    +0.10
    0.08
    Negative Logits
    Interstitial
    -0.70
    ¥µ
    -0.67
    TERN
    -0.64
    âĸ¬âĸ¬
    -0.63
    animate
    -0.63
    frey
    -0.62
    stration
    -0.60
    ãĥ¬
    -0.60
    ORGE
    -0.59
    cemic
    -0.59
    POSITIVE LOGITS
    ernel
    0.88
    ed
    0.85
    irts
    0.82
    atchewan
    0.79
    ozy
    0.78
    edIn
    0.78
    mallow
    0.76
    er
    0.76
    itudinal
    0.75
    hoff
    0.71
    Activations Density 5.366%

    No Known Activations