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. 14931
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically related to a character named Thorfinn Eiriksson and associated locations and details

    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
    204
    +0.17
    0.9%
    971
    +0.16
    0.8%
    314
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.17
    0.03
    690
    +0.16
    0.05
    1741
    +0.14
    0.00
    Negative Logits
    <bos>
    -0.90
     Derfor
    -0.60
    Schwe
    -0.58
    готовка
    -0.57
    __":
    
    -0.55
     witcher
    -0.54
    Dzięki
    -0.53
     Oblivion
    -0.52
     gundam
    -0.52
    ParallelGroup
    -0.52
    POSITIVE LOGITS
     Marvel
    0.90
     Thor
    0.89
    Marvel
    0.88
     ideolog
    0.78
    marvel
    0.77
    Thor
    0.76
     quoc
    0.75
     rafael
    0.73
     thuy
    0.72
     nomine
    0.71
    Activations Density 0.680%

    No Known Activations