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. 10-RES-JB
    6. 1012
    Prev
    Next
    INDEX
    Explanations

    the conjunction "but" that introduces contrasts or exceptions

    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.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.32
    1.7%
    555
    +0.14
    0.7%
    411
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1276
    +0.32
    0.07
    1677
    +0.14
    0.06
    555
    +0.14
    0.06
    Negative Logits
    <bos>
    -2.72
    public
    -0.72
    protected
    -0.69
    vector
    -0.67
    awt
    -0.67
    app
    -0.66
    System
    -0.66
    align
    -0.65
    array
    -0.65
    ret
    -0.65
    POSITIVE LOGITS
     impra
    1.91
     maneu
    1.85
     reluct
    1.83
     disagre
    1.81
     scrat
    1.80
     accla
    1.78
     milf
    1.75
     increa
    1.73
     madonna
    1.73
     shenan
    1.72
    Activations Density 0.095%

    No Known Activations