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 6144
    5. 8-RES_FS6144-JB
    6. 5497
    Prev
    Next
    INDEX
    Explanations

    language related to visual design, graphics, and user experience

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    578
    +0.12
    0.6%
    363
    +0.12
    0.5%
    307
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.06
    326
    +0.12
    0.05
    435
    +0.10
    0.03
    Negative Logits
    hood
    -0.89
    unin
    -0.78
    itude
    -0.77
    onte
    -0.76
    ridge
    -0.74
    doms
    -0.74
    rase
    -0.73
    cano
    -0.71
    shire
    -0.70
    holder
    -0.70
    POSITIVE LOGITS
     Designer
    1.03
     designers
    1.01
    Visual
    1.00
     designer
    0.99
     representation
    0.90
     visuals
    0.90
     design
    0.89
     illusions
    0.88
     fidelity
    0.88
    illusion
    0.87
    Activations Density 0.427%

    No Known Activations