© 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. 9068
    Prev
    Next
    INDEX
    Explanations

    years mentioned as 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_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
    288
    +0.11
    0.5%
    351
    +0.11
    0.5%
    187
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    598
    +0.11
    0.03
    306
    +0.11
    0.03
    146
    +0.09
    0.03
    Negative Logits
    hop
    -0.77
    edge
    -0.71
     ancest
    -0.66
    ndra
    -0.62
    uden
    -0.62
     acad
    -0.61
     edge
    -0.61
     rapport
    -0.61
     lawy
    -0.61
    Ship
    -0.60
    POSITIVE LOGITS
    å¹
    0.83
    -'
    0.80
    rpm
    0.76
    ixties
    0.74
    EGIN
    0.74
    orpor
    0.72
     onwards
    0.70
     ����
    0.70
     Schwarzenegger
    0.67
    chev
    0.67
    Activations Density 0.035%

    No Known Activations