© 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 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. 10968
    Prev
    Next
    INDEX
    Explanations

    official statements, memos, and emails

    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
    447
    +0.23
    1.1%
    567
    +0.10
    0.5%
    668
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.23
    0.04
    217
    +0.10
    0.03
    540
    +0.09
    0.04
    Negative Logits
     encounters
    -0.60
     races
    -0.59
     breeds
    -0.59
     extremes
    -0.58
     edges
    -0.56
     Flavoring
    -0.56
     journeys
    -0.55
     outcomes
    -0.55
     spills
    -0.55
     Yards
    -0.54
    POSITIVE LOGITS
     titled
    1.05
     thanking
    0.94
     entitled
    0.93
     stating
    0.92
     outlining
    0.90
     denouncing
    0.88
     urging
    0.88
     apologizing
    0.86
     saying
    0.84
     accusing
    0.84
    Activations Density 0.188%

    No Known Activations