© 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. 24286
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the name "James" 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
    218
    +0.12
    0.5%
    430
    +0.11
    0.5%
    346
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.12
    0.02
    559
    +0.11
    0.02
    218
    +0.11
    0.02
    Negative Logits
    yards
    -0.76
    favorite
    -0.73
    ebook
    -0.70
    ULAR
    -0.70
    spring
    -0.70
     hive
    -0.67
    adian
    -0.65
    ning
    -0.64
    qv
    -0.64
    sites
    -0.63
    POSITIVE LOGITS
     Comey
    0.95
    ITNESS
    0.93
     Clerk
    0.89
     Clapper
    0.87
     Mattis
    0.84
     Madison
    0.83
     Joyce
    0.80
     Webb
    0.80
     Cameron
    0.79
     Badge
    0.77
    Activations Density 0.009%

    No Known Activations