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 49152
    5. 8-RES_FS49152-JB
    6. 26117
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to agriculture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.20
    0.9%
    481
    +0.14
    0.7%
    575
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.02
    524
    +0.14
    0.02
    575
    +0.12
    0.02
    Negative Logits
    gettable
    -0.86
    hift
    -0.77
    opal
    -0.77
     Jenner
    -0.76
    onement
    -0.75
    ochet
    -0.68
    hov
    -0.68
    ocular
    -0.67
    POS
    -0.66
     Lumpur
    -0.66
    POSITIVE LOGITS
     subsidies
    0.88
     sector
    0.83
     ministry
    0.80
     labou
    0.79
     plants
    0.77
    iculture
    0.76
     industries
    0.75
     sectors
    0.74
     minister
    0.74
     farming
    0.74
    Activations Density 0.017%

    No Known Activations