© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 3072
    9. 8-RES_FS3072-JB
    11. 2976
    Prev
    Next
    INDEX
    Explanations

    names of individuals and locations, including specific dates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    90
    +0.13
    0.6%
    580
    +0.10
    0.5%
    77
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    580
    +0.13
    0.09
    90
    +0.10
    0.07
    331
    +0.10
    0.07
    Negative Logits
    otonin
    -0.77
    iatus
    -0.65
     Proposition
    -0.65
     Sunshine
    -0.64
    acket
    -0.62
     Lup
    -0.59
     Volcano
    -0.59
    ADVERTISEMENT
    -0.59
    ggle
    -0.59
    Newsletter
    -0.57
    POSITIVE LOGITS
     notwithstanding
    0.98
    wise
    0.86
    cause
    0.86
    tis
    0.79
    pecially
    0.76
    fortunately
    0.70
     thereof
    0.69
     alike
    0.68
    wx
    0.68
     permitting
    0.66
    Activations Density 2.535%

    No Known Activations