© 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. 7393
    Prev
    Next
    INDEX
    Explanations

    references to software and technology terms

    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
    362
    +0.21
    1.0%
    393
    +0.17
    0.8%
    684
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.21
    0.07
    393
    +0.17
    0.05
    608
    +0.09
    0.05
    Negative Logits
    abuse
    -0.81
    each
    -0.79
    rade
    -0.78
    POST
    -0.77
     beforehand
    -0.74
    ambo
    -0.73
    LOD
    -0.72
    Versions
    -0.72
    ago
    -0.71
     qualifies
    -0.70
    POSITIVE LOGITS
     culmination
    1.34
     largest
    1.25
     cornerstone
    1.21
     oldest
    1.20
     smallest
    1.19
     easiest
    1.19
     simplest
    1.19
     centerpiece
    1.16
     fastest
    1.14
     newest
    1.14
    Activations Density 0.157%

    No Known Activations