© 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. 10216
    Prev
    Next
    INDEX
    Explanations

    mentions of specific people and their actions or characteristics

    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
    430
    +0.12
    0.6%
    141
    +0.10
    0.5%
    39
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.12
    0.06
    149
    +0.10
    0.05
    757
    +0.10
    0.04
    Negative Logits
    bart
    -0.68
    CONCLUS
    -0.64
    "(
    -0.64
    VO
    -0.60
    $.
    -0.60
    SPA
    -0.60
     Conclusion
    -0.59
    %.
    -0.58
    ulp
    -0.58
    ".
    -0.58
    POSITIVE LOGITS
     hailed
    0.79
     originally
    0.79
     owns
    0.78
     spearheaded
    0.78
     operates
    0.77
     oversaw
    0.76
     presided
    0.74
     oversees
    0.74
     ostensibly
    0.74
     comprises
    0.73
    Activations Density 0.182%

    No Known Activations