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. 6798
    Prev
    Next
    INDEX
    Explanations

    words or terms associated with "Blake."

    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
    122
    +0.19
    1.1%
    1984
    +0.14
    0.8%
    1350
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    122
    +0.19
    0.02
    1984
    +0.14
    0.02
    757
    +0.13
    0.02
    Negative Logits
    <bos>
    -1.64
    Бележки
    -0.67
    Parcelize
    -0.64
    richTextPanel
    -0.61
     Caron
    -0.58
    Personendaten
    -0.57
    UnitTesting
    -0.57
     kasarigan
    -0.56
    uxxxx
    -0.56
    Referencie
    -0.56
    POSITIVE LOGITS
     Bla
    1.56
    Bla
    1.46
     bla
    1.36
     BLA
    1.30
     Blake
    1.25
    bla
    1.24
     blade
    1.21
     Blade
    1.21
    Blake
    1.17
    BLA
    1.14
    Activations Density 0.084%

    No Known Activations