© 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. 12005
    Prev
    Next
    INDEX
    Explanations

    words related to government, political events, and policies

    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
    437
    +0.14
    0.6%
    683
    +0.12
    0.6%
    365
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.14
    0.02
    683
    +0.12
    0.02
    365
    +0.12
    0.01
    Negative Logits
    Story
    -0.66
     sight
    -0.63
    EStreamFrame
    -0.59
     shotguns
    -0.58
    ãĥ¯ãĥ³
    -0.57
     advertisers
    -0.57
    fall
    -0.57
     Kenobi
    -0.57
    idine
    -0.56
     Maker
    -0.56
    POSITIVE LOGITS
    uce
    1.19
    icts
    1.19
    gew
    1.18
    ifice
    1.16
    nesday
    1.15
    monton
    1.14
    ict
    1.13
    inburgh
    1.07
    uctive
    1.06
    uct
    1.01
    Activations Density 0.021%

    No Known Activations