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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11328
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues or disputes

    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
    560
    +0.11
    0.5%
    420
    +0.10
    0.4%
    447
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    428
    +0.11
    0.04
    550
    +0.10
    0.04
    739
    +0.10
    0.02
    Negative Logits
    é¾įå¥ij士
    -0.91
    imeters
    -0.79
    quickShipAvailable
    -0.73
    mate
    -0.71
    irtual
    -0.70
    ²¾
    -0.64
    paren
    -0.64
    appropriate
    -0.63
    opathy
    -0.63
     guiActiveUn
    -0.63
    POSITIVE LOGITS
     Orn
    0.72
     Norfolk
    0.68
     Monk
    0.68
     Trilogy
    0.67
    igers
    0.67
     Tribunal
    0.66
     Fleet
    0.66
     Legions
    0.65
     Redemption
    0.65
    hest
    0.65
    Activations Density 0.477%

    No Known Activations