© 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 24576
    5. 8-RES_FS24576-JB
    6. 8004
    Prev
    Next
    INDEX
    Explanations

    hyperlinks

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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%
    594
    +0.09
    0.4%
    313
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.13
    -0.00
    208
    +0.09
    0.01
    313
    +0.09
    0.01
    Negative Logits
    ibles
    -0.59
     Kut
    -0.59
     Labrador
    -0.59
     Starship
    -0.58
    rators
    -0.56
     '[
    -0.56
     Dent
    -0.56
     Excellence
    -0.56
    ardless
    -0.56
    iors
    -0.55
    POSITIVE LOGITS
    /?
    0.79
    legraph
    0.79
    Thumbnail
    0.78
    biz
    0.78
    cdn
    0.75
    medi
    0.75
    ecd
    0.74
    isf
    0.72
    yssey
    0.71
    wp
    0.71
    Activations Density 0.018%

    No Known Activations