© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 19817
    Prev
    Next
    INDEX
    Explanations

    mentions of updating or modifying software applications and APIs

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    +0.21
    1.1%
    49
    +0.13
    0.6%
    7
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.21
    0.04
    373
    +0.13
    -0.01
    155
    +0.09
    0.04
    Negative Logits
    \\\\\\\\
    -0.78
    ĸļ
    -0.71
    ŃĶ
    -0.70
    ĸļ士
    -0.68
    vertising
    -0.68
     Beir
    -0.68
    emale
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£
    -0.67
    é¾įå¥
    -0.67
    Ě
    -0.67
    POSITIVE LOGITS
    !).
    0.56
    aned
    0.53
     Subjects
    0.50
    ].
    0.48
     anymore
    0.48
     modulation
    0.48
    .'"
    0.48
    '."
    0.48
     unused
    0.48
     ±
    0.48
    Activations Density 0.074%

    No Known Activations