© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7655
    Prev
    Next
    INDEX
    Explanations

    email-related content and discount promotion codes

    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
    124
    +0.12
    0.6%
    760
    +0.12
    0.5%
    409
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.12
    0.03
    760
    +0.12
    0.03
    565
    +0.12
    0.03
    Negative Logits
     Chi
    -0.81
    jit
    -0.77
     Holt
    -0.76
     Caleb
    -0.76
     Kath
    -0.75
    Hen
    -0.75
    kar
    -0.74
    rh
    -0.73
     Pinball
    -0.72
     Tosh
    -0.71
    POSITIVE LOGITS
    active
    1.03
    abled
    1.01
    ABLE
    0.99
    ileged
    0.98
    isible
    0.93
    accessible
    0.92
    igible
    0.90
    izable
    0.90
    able
    0.89
    sufficient
    0.88
    Activations Density 0.195%

    No Known Activations