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. 11252
    Prev
    Next
    INDEX
    Explanations

    references to Border Patrol related activities and issues

    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
    288
    +0.18
    0.8%
    422
    +0.11
    0.5%
    141
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.18
    0.02
    288
    +0.11
    0.02
    617
    +0.09
    0.02
    Negative Logits
    frey
    -0.72
    VERTISEMENT
    -0.72
    ynthesis
    -0.70
    iris
    -0.68
    earable
    -0.67
    ilts
    -0.66
    iple
    -0.66
    etics
    -0.66
    thora
    -0.65
    orf
    -0.65
    POSITIVE LOGITS
     crossings
    1.10
    lines
    1.01
    lands
    0.93
     Patrol
    0.90
    line
    0.89
     patrol
    0.89
     fence
    0.85
     crossing
    0.85
     Crossing
    0.85
     guards
    0.84
    Activations Density 0.020%

    No Known Activations