© 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. 7074
    Prev
    Next
    INDEX
    Explanations

    information about events and activities happening in a particular location and related to sports teams

    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
    500
    +0.12
    0.6%
    309
    +0.12
    0.5%
    459
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.07
    500
    +0.12
    0.05
    76
    +0.11
    0.05
    Negative Logits
    ecause
    -0.82
    overty
    -0.79
    pta
    -0.74
    tsky
    -0.72
    olitics
    -0.71
    utics
    -0.69
    vernment
    -0.68
     fundamentally
    -0.68
    ŃĶ
    -0.68
    ãĤ¨ãĥ«
    -0.68
    POSITIVE LOGITS
     specials
    0.93
     stickers
    0.86
     cameo
    0.85
     badges
    0.84
     subscription
    0.82
     narration
    0.82
     badge
    0.81
     coupon
    0.81
     commentary
    0.80
     playlist
    0.80
    Activations Density 0.426%

    No Known Activations