© 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. 8153
    Prev
    Next
    INDEX
    Explanations

    website-related content

    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
    447
    +0.13
    0.6%
    679
    +0.11
    0.5%
    481
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.13
    0.03
    247
    +0.11
    0.02
    644
    +0.11
    0.02
    Negative Logits
    heny
    -0.73
    erie
    -0.70
     ACTIONS
    -0.67
    ño
    -0.66
    agher
    -0.65
    olyn
    -0.64
    fle
    -0.62
    loe
    -0.61
    arching
    -0.61
    atory
    -0.61
    POSITIVE LOGITS
     www
    0.93
     homepage
    0.92
     hosting
    0.91
    pages
    0.89
     URL
    0.89
     URLs
    0.85
    erver
    0.80
    osphere
    0.77
     admins
    0.76
     hosted
    0.74
    Activations Density 0.037%

    No Known Activations