© 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 49152
    9. 8-RES_FS49152-JB
    11. 26600
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or commands

    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
    718
    +0.14
    0.7%
    326
    +0.12
    0.6%
    738
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.14
    0.04
    326
    +0.12
    0.02
    508
    +0.11
    0.02
    Negative Logits
    nces
    -0.69
    wives
    -0.65
    andowski
    -0.64
    ELD
    -0.63
    soType
    -0.62
    soDeliveryDate
    -0.62
    ensive
    -0.61
    ccording
    -0.60
     Klu
    -0.60
     outwe
    -0.59
    POSITIVE LOGITS
    ggles
    1.30
     activate
    1.24
     maximize
    1.09
     obtain
    1.04
     locate
    1.04
     toggle
    1.03
     ensure
    1.03
     customize
    1.02
     create
    1.01
     retrieve
    1.01
    Activations Density 0.049%

    No Known Activations