© 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. 22449
    Prev
    Next
    INDEX
    Explanations

    variations of the word "hand" and its derivatives, often in contexts related to control or manipulation

    oai_token-act-pair · gpt-4o-miniTriggered 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
    481
    +0.13
    0.6%
    159
    +0.13
    0.6%
    448
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.13
    0.04
    763
    +0.13
    0.04
    408
    +0.11
    0.05
    Negative Logits
    oother
    -0.89
    SEA
    -0.81
    URA
    -0.80
    ainers
    -0.78
    orthy
    -0.78
    ARC
    -0.76
    ector
    -0.75
    asio
    -0.75
    ainer
    -0.75
    hower
    -0.74
    POSITIVE LOGITS
     dismissal
    1.05
     banter
    1.04
     antics
    0.99
     humor
    0.98
     humour
    0.96
     optimism
    0.94
     criticism
    0.93
     explanations
    0.93
     insults
    0.93
     insin
    0.93
    Activations Density 0.182%

    No Known Activations