© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 696
    Prev
    Next
    INDEX
    Explanations

    instances of actions or events involving specific individuals or unnamed workers

    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
    522
    +0.11
    0.5%
    141
    +0.10
    0.5%
    129
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    264
    +0.11
    0.05
    233
    +0.10
    0.06
    522
    +0.09
    0.06
    Negative Logits
    ".
    -0.80
     ".
    -0.78
    $.
    -0.76
     ."
    -0.70
    +.
    -0.67
    ";
    -0.67
    %.
    -0.66
    "(
    -0.66
    `.
    -0.64
    ."
    -0.63
    POSITIVE LOGITS
     originally
    0.65
    actionDate
    0.65
     hailed
    0.62
     longest
    0.60
    *)
    0.60
    -)
    0.59
     oldest
    0.59
     ostensibly
    0.59
    ensibly
    0.58
    ItemThumbnailImage
    0.58
    Activations Density 1.470%

    No Known Activations