© 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. 26644
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Pat."

    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
    589
    +0.10
    0.4%
    461
    +0.10
    0.4%
    218
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.10
    0.02
    461
    +0.10
    0.02
    589
    +0.09
    0.01
    Negative Logits
    vous
    -0.73
    xual
    -0.68
    ADE
    -0.68
    Ļ½
    -0.64
    STD
    -0.64
     Monstrous
    -0.63
    ĺħ
    -0.63
    omething
    -0.62
     td
    -0.60
    hower
    -0.59
    POSITIVE LOGITS
    riots
    1.43
    riot
    1.43
    ricia
    1.42
    terson
    1.35
    rice
    1.26
    ients
    1.24
    rons
    1.24
    hetic
    1.18
    rol
    1.14
    rolled
    1.12
    Activations Density 0.008%

    No Known Activations