© 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. 3996
    Prev
    Next
    INDEX
    Explanations

    references to legal or political content, specifically related to legislation, government actions, and societal issues

    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
    447
    +0.14
    0.6%
    641
    +0.12
    0.5%
    7
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.14
    0.22
    566
    +0.12
    0.12
    641
    +0.11
    0.15
    Negative Logits
    oids
    -0.65
     ATK
    -0.62
     Boat
    -0.61
    cpp
    -0.60
    voy
    -0.59
     Bee
    -0.59
    oppers
    -0.58
    clave
    -0.58
    teness
    -0.58
     Brewer
    -0.57
    POSITIVE LOGITS
     structured
    0.79
     interact
    0.79
     behave
    0.78
     unfolded
    0.74
     shaping
    0.72
    pport
    0.71
     fared
    0.69
     differs
    0.69
    stood
    0.69
     proced
    0.69
    Activations Density 19.928%

    No Known Activations