© 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. 24251
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations and road numbers

    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
    314
    +0.12
    0.6%
    122
    +0.11
    0.5%
    447
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.12
    0.03
    693
    +0.11
    0.03
    719
    +0.10
    0.03
    Negative Logits
    estamp
    -0.77
    netflix
    -0.69
     Nanto
    -0.63
     Qi
    -0.63
    ¨
    -0.57
     Payton
    -0.57
     Keynes
    -0.56
    amina
    -0.56
    onic
    -0.56
    plom
    -0.56
    POSITIVE LOGITS
    RH
    0.77
     Revis
    0.77
    llan
    0.72
    VB
    0.71
     Overt
    0.69
     Extension
    0.69
    rd
    0.68
    A
    0.68
    âĢ²
    0.67
    ONSORED
    0.66
    Activations Density 0.085%

    No Known Activations