Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11135
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    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
    480
    +0.40
    2.0%
    87
    +0.22
    1.1%
    447
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.40
    0.05
    480
    +0.22
    0.02
    464
    +0.16
    0.05
    Negative Logits
     agre
    -0.70
    nesday
    -0.70
     sugg
    -0.67
    sic
    -0.67
     spons
    -0.64
    hetti
    -0.64
    conserv
    -0.62
     colle
    -0.62
    antically
    -0.61
     neighb
    -0.61
    POSITIVE LOGITS
     ILCS
    0.78
     IPM
    0.75
     Introduction
    0.66
     partName
    0.63
     HOU
    0.63
     DISTRICT
    0.63
     Received
    0.62
    7601
    0.61
     Shin
    0.60
     ·
    0.60
    Activations Density 0.306%

    No Known Activations