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. 621
    Prev
    Next
    INDEX
    Explanations

    the word "duck" appearing in the text

    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
    1328
    +0.23
    1.2%
    68
    +0.19
    1.0%
    101
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1328
    +0.23
    0.06
    690
    +0.19
    0.04
    1741
    +0.15
    0.00
    Negative Logits
    Vegeu
    -0.79
    <bos>
    -0.72
    Архівовано
    -0.69
    EndContext
    -0.67
    RectangleBorder
    -0.66
    ParallelGroup
    -0.65
    ("")]
    
    -0.63
     الرياضيه
    -0.61
    +#+
    -0.60
    FontOfSize
    -0.60
    POSITIVE LOGITS
     unspeak
    1.12
     maneu
    1.06
     reluct
    1.05
     Duck
    1.03
     apprehen
    1.02
    Duck
    1.01
     pamph
    1.00
     philanth
    1.00
     duck
    0.99
     gaily
    0.98
    Activations Density 0.497%

    No Known Activations