© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 9276
    Prev
    Next
    INDEX
    Explanations

    past tense verbs related to scientific or medical activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    +0.18
    0.8%
    566
    +0.12
    0.5%
    308
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.18
    0.07
    344
    +0.12
    0.07
    552
    +0.10
    0.07
    Negative Logits
    ilings
    -0.67
    PI
    -0.65
    oshenko
    -0.63
    ethy
    -0.61
     Today
    -0.60
    bery
    -0.59
    orph
    -0.57
    alias
    -0.57
     currently
    -0.57
    owe
    -0.56
    POSITIVE LOGITS
    iths
    1.04
     been
    0.98
     begun
    0.92
     undergone
    0.90
    hers
    0.85
     gotten
    0.81
     originally
    0.81
    rons
    0.78
     hoped
    0.78
     gone
    0.77
    Activations Density 0.148%

    No Known Activations