© 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. 37543
    Prev
    Next
    INDEX
    Explanations

    varied forms of the word "on" in different contexts

    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%
    108
    +0.09
    0.4%
    219
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.13
    -0.00
    406
    +0.09
    0.01
    284
    +0.09
    0.01
    Negative Logits
     Izan
    -0.76
     Contrast
    -0.66
    ILA
    -0.65
     Siren
    -0.65
     destro
    -0.63
     arteries
    -0.62
    Redd
    -0.60
     captcha
    -0.59
     Jinn
    -0.59
     Lith
    -0.58
    POSITIVE LOGITS
    isco
    0.92
    ruary
    0.86
    furt
    0.80
    ulent
    0.75
    atism
    0.74
    rance
    0.72
    ateurs
    0.70
    imore
    0.67
    nce
    0.67
    ophile
    0.66
    Activations Density 0.018%

    No Known Activations