© 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. 7442
    Prev
    Next
    INDEX
    Explanations

    quotes or statements related to legal matters or political commentary

    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
    314
    +0.14
    0.6%
    675
    +0.10
    0.5%
    102
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.14
    0.09
    48
    +0.10
    0.06
    504
    +0.09
    0.06
    Negative Logits
     federation
    -0.71
     seiz
    -0.70
     sacrific
    -0.68
     Negro
    -0.67
     ende
    -0.67
     Orchestra
    -0.65
     blot
    -0.63
    iolet
    -0.63
     strugg
    -0.62
     vulner
    -0.61
    POSITIVE LOGITS
    ¯
    1.07
    ï¸ı
    0.99
    cue
    0.89
    âĢł
    0.88
    STEM
    0.87
    which
    0.82
    s
    0.78
    °
    0.77
    £
    0.75
    âĻ¦
    0.74
    Activations Density 0.172%

    No Known Activations