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 · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 14704
    Prev
    Next
    INDEX
    Explanations

    shoe-related terms, particularly focusing on different parts and materials of shoes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    251
    +0.17
    0.9%
    920
    +0.17
    0.9%
    1262
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1328
    +0.17
    0.05
    1363
    +0.17
    0.04
    690
    +0.15
    0.04
    Negative Logits
    <bos>
    -0.85
     يتيمه
    -0.64
     Beaucoup
    -0.61
     tæn
    -0.60
     Seulement
    -0.60
    Kx
    -0.59
     Maintenant
    -0.57
     fta
    -0.57
    fdb
    -0.54
     Taylor
    -0.54
    POSITIVE LOGITS
     heel
    0.80
     Heel
    0.73
     Brett
    0.72
     heels
    0.72
    Heel
    0.71
    Brett
    0.71
     Patrick
    0.66
     Heels
    0.62
    heel
    0.59
    Patrick
    0.59
    Activations Density 0.766%

    No Known Activations