© 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. 17679
    Prev
    Next
    INDEX
    Explanations

    capital letters, special characters, and random letter sequences

    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
    634
    +0.11
    0.5%
    308
    +0.10
    0.4%
    524
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.11
    0.03
    107
    +0.10
    0.02
    524
    +0.08
    0.02
    Negative Logits
     chunks
    -0.76
     tuna
    -0.72
     censored
    -0.72
     loopholes
    -0.71
     unborn
    -0.69
     eyeb
    -0.68
     Pengu
    -0.66
     omega
    -0.64
     Turing
    -0.64
     incorpor
    -0.64
    POSITIVE LOGITS
    ï¸ı
    1.16
    Å
    1.05
    ng
    1.02
    ti
    1.01
    ski
    0.98
    ÃŃn
    0.97
    t
    0.95
    §
    0.94
    tal
    0.93
    Ã
    0.93
    Activations Density 0.040%

    No Known Activations