© 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 24576
    9. 8-RES_FS24576-JB
    11. 20321
    Prev
    Next
    INDEX
    Explanations

    companies, businesses, or organizations and their operations or 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
    480
    +0.21
    1.0%
    24
    +0.10
    0.5%
    756
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    351
    +0.21
    0.05
    408
    +0.10
    0.10
    393
    +0.10
    0.12
    Negative Logits
    ebin
    -0.82
     Yesterday
    -0.76
     HERE
    -0.75
    Update
    -0.72
    ctuary
    -0.72
     WATCH
    -0.72
     UPDATE
    -0.70
     Recently
    -0.64
     [+
    -0.63
     Appears
    -0.63
    POSITIVE LOGITS
     lacked
    0.93
     mattered
    0.92
     tended
    0.88
     depended
    0.88
     feared
    0.83
     reasoned
    0.78
     knew
    0.77
     consisted
    0.77
     resembled
    0.77
     hated
    0.77
    Activations Density 1.941%

    No Known Activations