© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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 49152
    9. 8-RES_FS49152-JB
    11. 45451
    Prev
    Next
    INDEX
    Explanations

    rhetorical questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    373
    +0.13
    0.6%
    679
    +0.12
    0.6%
    481
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.13
    0.01
    679
    +0.12
    0.01
    391
    +0.11
    0.01
    Negative Logits
     srf
    -0.81
    emaker
    -0.76
    Þ
    -0.73
    İĭ
    -0.72
    ailability
    -0.68
     rall
    -0.67
    ModLoader
    -0.66
     skelet
    -0.66
    ¥ŀ
    -0.66
     obser
    -0.65
    POSITIVE LOGITS
     Fuck
    0.97
     Nobody
    0.91
     Nothing
    0.86
     Anyway
    0.85
     Aren
    0.82
     Everybody
    0.82
     Actually
    0.81
    fuck
    0.81
     Whenever
    0.81
     Nope
    0.80
    Activations Density 0.027%

    No Known Activations