© 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 12288
    9. 8-RES_FS12288-JB
    11. 10117
    Prev
    Next
    INDEX
    Explanations

    terms related to business and legal matters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    480
    +0.50
    2.7%
    87
    +0.22
    1.2%
    266
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.50
    0.10
    480
    +0.22
    0.04
    288
    +0.17
    0.12
    Negative Logits
    rooms
    -0.76
    eworks
    -0.75
    assies
    -0.75
    sites
    -0.74
     Vaugh
    -0.70
    ernels
    -0.70
    drops
    -0.69
    places
    -0.66
     Rooms
    -0.66
    lees
    -0.66
    POSITIVE LOGITS
     standpoint
    0.70
    ixtape
    0.66
     perspective
    0.65
     statement
    0.64
     variant
    0.64
     piece
    0.62
     sample
    0.62
     spokesperson
    0.62
     article
    0.61
     approximation
    0.61
    Activations Density 0.961%

    No Known Activations