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. 11206
    Prev
    Next
    INDEX
    Explanations

    words related to physical fitness or health

    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
    459
    +0.11
    0.5%
    255
    +0.10
    0.5%
    21
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.11
    0.01
    46
    +0.10
    0.01
    225
    +0.10
    0.01
    Negative Logits
    wcs
    -0.76
    kefeller
    -0.68
     Lak
    -0.66
    externalActionCode
    -0.66
    clips
    -0.62
    asta
    -0.61
    irie
    -0.61
    theless
    -0.61
    etheless
    -0.60
     Roads
    -0.60
    POSITIVE LOGITS
    ters
    1.10
    gerald
    1.07
    nah
    0.96
    ments
    0.93
    ably
    0.83
    bit
    0.81
    MENTS
    0.80
    ament
    0.80
    ment
    0.80
     snug
    0.79
    Activations Density 0.016%

    No Known Activations