© 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 EvalsExportsinterp-engineNEWAPI 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. 5251
    Prev
    Next
    INDEX
    Explanations

    information related to video game communities and forums

    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
    526
    +0.12
    0.6%
    167
    +0.11
    0.5%
    421
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    421
    +0.12
    0.01
    232
    +0.11
    0.01
    347
    +0.11
    0.01
    Negative Logits
     consec
    -0.72
     politic
    -0.68
    FUL
    -0.66
     combustion
    -0.66
     dissolved
    -0.64
    WARD
    -0.62
     condem
    -0.61
     fitting
    -0.60
     repro
    -0.60
     chemotherapy
    -0.60
    POSITIVE LOGITS
    blers
    1.27
    estate
    1.11
    estone
    1.07
    elines
    1.05
    etime
    1.05
    azing
    1.03
    owitz
    1.03
    bitious
    1.02
    eline
    1.01
    ulative
    1.01
    Activations Density 0.015%

    No Known Activations