© 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. 9007
    Prev
    Next
    INDEX
    Explanations

    telephone numbers and promotional codes

    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
    614
    +0.10
    0.4%
    474
    +0.09
    0.4%
    711
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    605
    +0.10
    0.02
    182
    +0.09
    0.01
    227
    +0.09
    0.01
    Negative Logits
     Nat
    -0.82
     Canad
    -0.79
     Cosponsors
    -0.79
    Nat
    -0.78
     Resp
    -0.77
     Survivors
    -0.77
     Synd
    -0.77
    istant
    -0.76
     Anth
    -0.74
     Nost
    -0.74
    POSITIVE LOGITS
    6
    1.47
     6
    1.30
    six
    0.95
    7
    0.93
    06
    0.92
     06
    0.90
    osite
    0.89
    ocl
    0.87
    628
    0.86
     Sixth
    0.86
    Activations Density 0.077%

    No Known Activations