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 3072
    5. 8-RES_FS3072-JB
    6. 1591
    Prev
    Next
    INDEX
    Explanations

    mentions of people and events related to various incidents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    373
    +0.17
    0.8%
    361
    +0.12
    0.6%
    640
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.17
    0.15
    160
    +0.12
    0.10
    373
    +0.12
    -0.03
    Negative Logits
     veter
    -0.67
    catentry
    -0.63
     LX
    -0.63
     MPG
    -0.62
     Anonymous
    -0.61
     LD
    -0.60
     GPL
    -0.57
    429
    -0.56
     flaming
    -0.56
    rists
    -0.56
    POSITIVE LOGITS
    '."
    0.70
    farious
    0.69
    ãĤ¨ãĥ«
    0.68
    Speaking
    0.67
    ',"
    0.66
    window
    0.63
    ensation
    0.63
    ]).
    0.62
    plings
    0.62
     compr
    0.61
    Activations Density 0.745%

    No Known Activations