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. 11372
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenges and solutions in various fields such as education, law, space exploration, and urban planning

    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
    68
    +0.10
    0.5%
    378
    +0.10
    0.4%
    340
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    733
    +0.10
    0.04
    340
    +0.10
    0.05
    330
    +0.10
    0.05
    Negative Logits
    achus
    -0.88
    osate
    -0.81
    terness
    -0.76
    onis
    -0.74
    ppe
    -0.72
     Pwr
    -0.69
    owder
    -0.69
    lett
    -0.68
    igation
    -0.68
    let
    -0.67
    POSITIVE LOGITS
     sorts
    1.22
     kinds
    1.22
     types
    1.01
     shores
    0.94
     proceedings
    0.93
     facts
    0.91
     developments
    0.88
     truths
    0.87
     endeavors
    0.86
     establishments
    0.86
    Activations Density 0.107%

    No Known Activations