© 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. 5217
    Prev
    Next
    INDEX
    Explanations

    phrases expressing positive sentiments or affirmations

    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
    608
    +0.11
    0.5%
    665
    +0.09
    0.4%
    185
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.11
    0.04
    608
    +0.09
    0.04
    665
    +0.09
    0.03
    Negative Logits
    calling
    -0.76
    icipated
    -0.69
    é¾įå¥ij士
    -0.69
     objections
    -0.63
     objectionable
    -0.63
    ively
    -0.62
    uli
    -0.62
    Recommended
    -0.61
    soDeliveryDate
    -0.61
    rising
    -0.61
    POSITIVE LOGITS
     hear
    1.02
     behold
    1.01
     remind
    1.00
     learn
    0.98
     revisit
    0.97
     see
    0.96
    ggles
    0.94
     realize
    0.90
     compare
    0.89
     emulate
    0.87
    Activations Density 0.069%

    No Known Activations