© 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. 2151
    Prev
    Next
    INDEX
    Explanations

    information related to data and analysis

    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
    481
    +0.16
    0.7%
    447
    +0.12
    0.5%
    393
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.16
    0.04
    120
    +0.12
    0.04
    393
    +0.10
    0.04
    Negative Logits
    hei
    -0.73
    ovo
    -0.73
    agall
    -0.73
    successfully
    -0.73
    conn
    -0.70
    psc
    -0.70
    ©¶æ¥µ
    -0.70
    gado
    -0.70
    uel
    -0.69
    ibr
    -0.68
    POSITIVE LOGITS
     explanations
    1.10
     info
    1.08
     tips
    1.04
     screenshots
    1.02
     definitions
    1.01
     FAQ
    0.99
     directions
    0.99
     insights
    0.97
     specifications
    0.97
     statistics
    0.97
    Activations Density 0.177%

    No Known Activations