© 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. 9714
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "so many" is used

    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
    481
    +0.12
    0.5%
    593
    +0.10
    0.5%
    15
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.12
    0.02
    15
    +0.10
    0.03
    458
    +0.09
    0.02
    Negative Logits
    UAL
    -0.79
    ħĭ
    -0.76
    afort
    -0.73
    ivism
    -0.72
    hern
    -0.70
    owder
    -0.67
    ¶æ
    -0.67
    vertisement
    -0.67
    ADVERTISEMENT
    -0.66
    ¾
    -0.65
    POSITIVE LOGITS
     times
    1.09
     unanswered
    1.07
     facets
    0.95
     conflicting
    0.92
     variables
    0.92
     occasions
    0.91
     people
    0.91
     instances
    0.86
     aspects
    0.85
     cooks
    0.84
    Activations Density 0.038%

    No Known Activations