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

    Neuronpedia

    Jacobian LensNEW
    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. 42994
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in."

    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
    77
    +0.11
    0.5%
    483
    +0.10
    0.5%
    9
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    483
    +0.11
    0.01
    131
    +0.10
    0.01
    88
    +0.10
    0.01
    Negative Logits
    incial
    -0.76
    uterte
    -0.73
    ailability
    -0.71
    estyles
    -0.71
    Published
    -0.70
    bilt
    -0.69
    umenthal
    -0.67
    vice
    -0.66
    aptic
    -0.66
    psey
    -0.64
    POSITIVE LOGITS
    clus
    0.90
     lieu
    0.84
    lihood
    0.82
    animate
    0.81
    liest
    0.76
    organic
    0.76
     spite
    0.75
    clusively
    0.73
    lier
    0.71
    ducers
    0.69
    Activations Density 0.015%

    No Known Activations