© 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. 8840
    Prev
    Next
    INDEX
    Explanations

    references to sports seasons and player contracts

    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
    575
    +0.15
    0.7%
    78
    +0.11
    0.5%
    274
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.15
    0.05
    274
    +0.11
    0.04
    575
    +0.10
    0.04
    Negative Logits
    dit
    -0.66
    ogle
    -0.65
    sight
    -0.65
    rity
    -0.65
     encl
    -0.63
    creen
    -0.63
     instantaneous
    -0.61
    hai
    -0.61
    ropy
    -0.60
    gall
    -0.60
    POSITIVE LOGITS
     opener
    1.13
     finale
    1.08
    Coach
    0.86
     unbeaten
    0.83
     coached
    0.76
     coaching
    0.76
    bleacher
    0.75
     Coach
    0.72
     coach
    0.71
     Playoffs
    0.69
    Activations Density 0.051%

    No Known Activations