© 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. 34714
    Prev
    Next
    INDEX
    Explanations

    special characters like parentheses, slashes, and other symbols

    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
    463
    +0.08
    0.5%
    205
    +0.07
    0.4%
    487
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    166
    +0.08
    0.10
    23
    +0.07
    0.11
    253
    +0.07
    0.11
    Negative Logits
     invari
    -0.52
     nas
    -0.47
     Siberia
    -0.43
     rack
    -0.43
     subt
    -0.43
     Stevenson
    -0.43
    arette
    -0.42
     Seym
    -0.42
     Recomm
    -0.42
     retreat
    -0.41
    POSITIVE LOGITS
    ãĥĦ
    0.62
    *)
    0.59
    abama
    0.58
    RPG
    0.57
    ?:
    0.56
    artifacts
    0.55
    ahu
    0.55
    \\
    0.55
    browser
    0.53
    Bat
    0.53
    Activations Density 3.656%

    No Known Activations