© 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. 21021
    Prev
    Next
    INDEX
    Explanations

    phrases indicating instructions or actions to take next

    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
    570
    +0.09
    0.4%
    114
    +0.09
    0.4%
    623
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    623
    +0.09
    0.01
    355
    +0.09
    0.01
    766
    +0.09
    0.01
    Negative Logits
    roots
    -0.71
    ³³³³³³³³
    -0.70
    ³³³³³³³³³³³³³³³³
    -0.70
    ³³³³
    -0.61
    etts
    -0.58
    pecting
    -0.57
    toe
    -0.56
     Penal
    -0.56
    owship
    -0.55
    ³³
    -0.55
    POSITIVE LOGITS
     Invalid
    0.95
    ality
    0.79
    ally
    0.76
    atta
    0.68
    ãģ®
    0.65
     regretted
    0.64
    aneously
    0.64
    osta
    0.64
    iator
    0.64
     delete
    0.63
    Activations Density 0.010%

    No Known Activations