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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19229
    Prev
    Next
    INDEX
    Explanations

    leaked or confidential information

    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
    362
    +0.12
    0.6%
    91
    +0.12
    0.5%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    91
    +0.12
    0.04
    680
    +0.12
    0.03
    656
    +0.10
    0.03
    Negative Logits
    tics
    -0.98
    apo
    -0.94
    eeks
    -0.87
    anship
    -0.85
    ertodd
    -0.85
    aido
    -0.82
    rats
    -0.82
    abiding
    -0.81
    addafi
    -0.81
    cellence
    -0.80
    POSITIVE LOGITS
     version
    1.11
     correspondence
    1.11
     memorandum
    1.10
     documents
    1.06
     document
    1.04
     statement
    1.04
     memo
    1.01
     questionnaire
    1.00
     letter
    0.99
     transcript
    0.97
    Activations Density 0.137%

    No Known Activations