Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 6144
    5. 8-RES_FS6144-JB
    6. 5541
    Prev
    Next
    INDEX
    Explanations

    Tokens that introduce or modify clauses, often connecting ideas or providing context in complex sentences. These include conjunctions, prepositions, and relative pronouns that help structure the flow of information in the text.

    eleuther_acts_top20 · claude-3-5-sonnet-20240620Triggered by @jake

    safety instructions and precautions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.96
    38.3%
    138
    +0.26
    10.4%
    64
    +0.01
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.96
    1.00
    447
    +0.26
    0.99
    64
    +0.01
    -0.01
    Negative Logits
     Azerb
    -0.04
    elsius
    -0.04
    Þ
    -0.04
    ij士
    -0.04
    oÄŁ
    -0.04
     guiActiveUn
    -0.04
    ñ
    -0.03
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.03
    £ı
    -0.03
     Vaugh
    -0.03
    POSITIVE LOGITS
    ↵
    0.05
    ,
    0.05
     the
    0.04
    The
    0.04
    -
    0.04
    .
    0.04
     and
    0.04
     in
    0.04
     to
    0.04
     of
    0.04
    Activations Density 3.176%

    No Known Activations