© 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 24576
    9. 8-RES_FS24576-JB
    11. 24291
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sparagus" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    504
    +0.11
    0.5%
    211
    +0.11
    0.5%
    349
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.11
    0.01
    406
    +0.11
    0.01
    504
    +0.10
    0.01
    Negative Logits
    ħĭ
    -0.78
    hirt
    -0.70
     Territories
    -0.68
    sburg
    -0.67
    ¥µ
    -0.67
    ãĥīãĥ©
    -0.64
    doms
    -0.62
     Carbuncle
    -0.62
    ĪĴ
    -0.62
    BOOK
    -0.62
    POSITIVE LOGITS
    allel
    1.33
    liament
    1.13
    anoia
    1.02
    ison
    0.93
    ities
    0.90
    cel
    0.90
    alysis
    0.90
    imony
    0.90
    ietal
    0.87
    ity
    0.87
    Activations Density 0.009%

    No Known Activations