© 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 12288
    9. 8-RES_FS12288-JB
    11. 10176
    Prev
    Next
    INDEX
    Explanations

    positive social and community-related content

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    87
    +0.28
    1.5%
    756
    +0.11
    0.6%
    459
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.28
    0.16
    575
    +0.11
    0.12
    459
    +0.10
    0.09
    Negative Logits
    ITNESS
    -0.64
     Canaver
    -0.58
    ettel
    -0.49
     Anthem
    -0.44
     Procedure
    -0.44
    atcher
    -0.43
    Ķ
    -0.42
    istrate
    -0.42
    affer
    -0.42
    ãĥ¤
    -0.42
    POSITIVE LOGITS
     and
    1.07
     or
    1.02
     &
    0.85
     etc
    0.82
     AND
    0.80
    -,
    0.69
    /
    0.67
    /
    0.65
    /.
    0.65
     et
    0.62
    Activations Density 1.839%

    No Known Activations