© 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. 26657
    Prev
    Next
    INDEX
    Explanations

    words that indicate common practices or norms

    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
    101
    +0.12
    0.5%
    724
    +0.11
    0.5%
    421
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.12
    0.02
    151
    +0.11
    0.02
    101
    +0.09
    0.02
    Negative Logits
    INC
    -0.70
     Orchestra
    -0.64
    amins
    -0.64
    bern
    -0.63
    eday
    -0.63
     possibly
    -0.63
     Vital
    -0.61
    Wr
    -0.60
     Kut
    -0.60
    Posts
    -0.59
    POSITIVE LOGITS
    entimes
    0.82
     consist
    0.81
     consists
    0.81
     comprise
    0.76
     abbrevi
    0.76
     consisted
    0.74
    ãĤ©
    0.74
     disclaim
    0.74
     refers
    0.73
     comprised
    0.73
    Activations Density 0.026%

    No Known Activations