© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 45652
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Here" in various contexts

    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
    314
    +0.11
    0.5%
    377
    +0.11
    0.5%
    294
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.11
    0.03
    276
    +0.11
    0.03
    136
    +0.10
    0.03
    Negative Logits
     Archdemon
    -0.71
    ONSORED
    -0.70
    natureconservancy
    -0.65
    acci
    -0.61
     Strait
    -0.59
    osc
    -0.58
    Closure
    -0.55
     elim
    -0.54
    efe
    -0.54
     manpower
    -0.53
    POSITIVE LOGITS
    tical
    1.23
    tics
    1.19
    abouts
    1.17
    tic
    1.04
     Comes
    1.02
    itia
    0.84
    after
    0.83
    endix
    0.80
    ford
    0.78
    ibaba
    0.78
    Activations Density 0.028%

    No Known Activations