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. 12-RES-JB
    6. 7864
    Prev
    Next
    INDEX
    Explanations

    occurrences of the pronoun "you."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.48
    2.0%
    2019
    +0.10
    0.4%
    204
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.48
    0.19
    1415
    +0.10
    0.13
    331
    +0.10
    0.10
    Negative Logits
    <bos>
    -1.98
     ã
    -0.70
     lomb
    -0.66
     MÁ
    -0.65
     Chá
    -0.63
     polie
    -0.63
     poliester
    -0.63
     bú
    -0.62
     universale
    -0.61
     ù
    -0.60
    POSITIVE LOGITS
     disgra
    0.91
     accla
    0.90
     maneu
    0.85
     practition
    0.81
     chrysler
    0.80
     idéale
    0.79
     perfet
    0.78
     inev
    0.77
     heapq
    0.76
     reluct
    0.76
    Activations Density 0.802%

    No Known Activations