© 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. 12499
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and political or social issues

    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
    87
    +0.21
    1.0%
    373
    +0.15
    0.7%
    756
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.10
    575
    +0.15
    0.09
    225
    +0.10
    0.08
    Negative Logits
     consolation
    -0.49
     OFFIC
    -0.47
     standalone
    -0.47
     unanimous
    -0.47
     slee
    -0.46
     aber
    -0.46
     somet
    -0.46
     ain
    -0.45
     omission
    -0.45
     caution
    -0.44
    POSITIVE LOGITS
     thereof
    0.95
     of
    0.87
    naires
    0.62
    iru
    0.59
    aires
    0.58
    iaz
    0.58
    worm
    0.57
    .''.
    0.56
    illas
    0.56
    aments
    0.56
    Activations Density 0.744%

    No Known Activations