© 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 3072
    9. 8-RES_FS3072-JB
    11. 678
    Prev
    Next
    INDEX
    Explanations

    information related to statistics and data analysis

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    747
    +0.12
    0.6%
    71
    +0.11
    0.5%
    66
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.12
    0.05
    35
    +0.11
    0.06
    747
    +0.09
    0.05
    Negative Logits
    rology
    -0.72
    £ı
    -0.63
    RAW
    -0.63
    ommel
    -0.62
    pired
    -0.60
    apest
    -0.59
    anners
    -0.58
    nis
    -0.56
    duino
    -0.56
    umbn
    -0.55
    POSITIVE LOGITS
     leaps
    0.84
    factor
    0.82
     dramatically
    0.74
     folds
    0.72
    fold
    0.72
     magnitude
    0.71
     precip
    0.68
    aby
    0.68
     fold
    0.68
    dB
    0.67
    Activations Density 1.862%

    No Known Activations