© 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. 18703
    Prev
    Next
    INDEX
    Explanations

    references to a specific person's name

    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
    +0.12
    0.6%
    80
    +0.10
    0.5%
    189
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    588
    +0.12
    0.01
    284
    +0.10
    0.01
    299
    +0.09
    0.01
    Negative Logits
    netflix
    -0.80
     Dominion
    -0.72
    lift
    -0.71
    WARD
    -0.69
    jet
    -0.69
    jin
    -0.68
    hood
    -0.67
    cloth
    -0.64
    current
    -0.62
    Cause
    -0.62
    POSITIVE LOGITS
    ician
    1.00
    olit
    0.88
    ano
    0.87
    ancies
    0.83
    ary
    0.82
    inelli
    0.81
    opol
    0.81
    icians
    0.80
    eness
    0.76
    aly
    0.76
    Activations Density 0.018%

    No Known Activations