© 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. 19697
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or exerting control in a forceful manner

    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
    35
    +0.10
    0.5%
    476
    +0.09
    0.4%
    516
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.10
    0.02
    516
    +0.09
    0.02
    70
    +0.09
    0.02
    Negative Logits
     IMAGES
    -0.77
    lihood
    -0.74
    enegger
    -0.73
     abund
    -0.68
     Nations
    -0.64
     Values
    -0.63
    xual
    -0.62
     Plenty
    -0.62
    IVES
    -0.62
     Aires
    -0.61
    POSITIVE LOGITS
    tered
    1.53
    tering
    1.40
    ters
    1.07
    down
    1.04
    tle
    1.04
    downs
    1.02
     down
    0.99
    outs
    0.91
    out
    0.90
    ulence
    0.90
    Activations Density 0.023%

    No Known Activations