© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 41566
    Prev
    Next
    INDEX
    Explanations

    terms related to quick or immediate actions and responses

    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
    240
    +0.12
    0.6%
    262
    +0.10
    0.4%
    160
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    262
    +0.12
    0.02
    105
    +0.10
    0.02
    307
    +0.09
    0.02
    Negative Logits
    gdala
    -0.98
    ationally
    -0.74
    ¥µ
    -0.69
    agine
    -0.68
    orers
    -0.66
     allerg
    -0.66
    pheus
    -0.66
    BIP
    -0.65
    initely
    -0.64
    yip
    -0.64
    POSITIVE LOGITS
     halt
    0.90
    return
    0.88
    idious
    0.88
     dispatch
    0.86
    ness
    0.85
    response
    0.83
    itude
    0.83
    motion
    0.80
     terminate
    0.80
     succession
    0.79
    Activations Density 0.033%

    No Known Activations