© 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. 18467
    Prev
    Next
    INDEX
    Explanations

    locations or specific geographical regions

    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
    553
    +0.12
    0.6%
    314
    +0.11
    0.5%
    11
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    11
    +0.12
    0.01
    326
    +0.11
    0.01
    289
    +0.11
    0.01
    Negative Logits
     NCT
    -0.75
    arnaev
    -0.71
    DonaldTrump
    -0.71
    PsyNetMessage
    -0.67
    ASED
    -0.66
    amins
    -0.65
     Clause
    -0.63
    ufact
    -0.62
     Chatt
    -0.62
     Polit
    -0.61
    POSITIVE LOGITS
    pipe
    1.00
    indal
    0.95
    ophon
    0.85
    sey
    0.84
    church
    0.82
    ed
    0.82
    wig
    0.82
    beck
    0.81
    bill
    0.81
    spr
    0.81
    Activations Density 0.014%

    No Known Activations