© 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. 9673
    Prev
    Next
    INDEX
    Explanations

    unusual or significant spots or locations within a context

    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
    651
    +0.12
    0.6%
    289
    +0.10
    0.5%
    187
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.12
    0.03
    95
    +0.10
    0.02
    686
    +0.10
    0.02
    Negative Logits
    issance
    -0.89
    yss
    -0.74
     pend
    -0.68
     godd
    -0.64
    ullivan
    -0.63
    racuse
    -0.62
     adolesc
    -0.61
    RR
    -0.61
    jri
    -0.61
    perty
    -0.60
    POSITIVE LOGITS
    lights
    1.52
    light
    1.03
    ter
    1.02
    lighting
    1.00
    ting
    0.98
    ty
    0.96
    tery
    0.96
    pots
    0.96
    ters
    0.96
    eele
    0.92
    Activations Density 0.075%

    No Known Activations