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. 46011
    Prev
    Next
    INDEX
    Explanations

    references to salads

    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
    +0.13
    0.6%
    16
    +0.10
    0.4%
    677
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.13
    0.01
    677
    +0.10
    0.01
    401
    +0.09
    0.01
    Negative Logits
    venants
    -0.76
    redit
    -0.75
     Borders
    -0.75
    ledged
    -0.73
    founded
    -0.69
    ITNESS
    -0.67
     Witness
    -0.67
    hovah
    -0.65
    urrencies
    -0.64
    rahim
    -0.62
    POSITIVE LOGITS
     dressing
    1.05
     greens
    1.02
     salad
    1.01
     salads
    0.98
     bowl
    0.96
    bowl
    0.94
     dress
    0.90
    eria
    0.88
     veggies
    0.83
     Bowl
    0.82
    Activations Density 0.004%

    No Known Activations