© 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 49152
    9. 8-RES_FS49152-JB
    11. 37324
    Prev
    Next
    INDEX
    Explanations

    phrases indicating results or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    16
    +0.10
    0.5%
    690
    +0.10
    0.4%
    291
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.02
    16
    +0.10
    0.02
    608
    +0.10
    0.02
    Negative Logits
    ener
    -0.83
    inks
    -0.83
    iste
    -0.75
    ãĤ¼ãĤ¦ãĤ¹
    -0.72
    pload
    -0.71
    orthy
    -0.71
    resses
    -0.69
    pter
    -0.68
    forward
    -0.66
    ulla
    -0.65
    POSITIVE LOGITS
     investigations
    0.96
     tests
    0.94
     investigation
    0.94
     preliminary
    0.91
     examinations
    0.91
     evaluations
    0.88
     elections
    0.87
     autopsy
    0.86
     testing
    0.85
     surveys
    0.84
    Activations Density 0.042%

    No Known Activations