© 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. 37292
    Prev
    Next
    INDEX
    Explanations

    temporal references and durations

    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
    87
    +0.30
    1.7%
    373
    +0.15
    0.8%
    680
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.30
    -0.02
    680
    +0.15
    0.04
    147
    +0.12
    0.03
    Negative Logits
    .",
    -0.65
    vantage
    -0.63
    .","
    -0.61
    .,"
    -0.61
    !".
    -0.58
     Pwr
    -0.57
    .�
    -0.57
    "...
    -0.56
    .:
    -0.55
    cause
    -0.54
    POSITIVE LOGITS
     hindsight
    0.88
     anecdotal
    0.62
     debates
    0.58
     aforementioned
    0.55
     concerted
    0.55
     pund
    0.54
     debunk
    0.53
     litigation
    0.53
     retrospect
    0.53
     unanim
    0.52
    Activations Density 0.466%

    No Known Activations