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. 876
    Prev
    Next
    INDEX
    Explanations

    references to the city of Austin

    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
    +0.15
    0.9%
    241
    +0.12
    0.7%
    1350
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.15
    0.02
    1335
    +0.12
    0.02
    241
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.14
    ⓧ
    -0.77
    více
    -0.74
    lepší
    -0.74
    
    
    -0.68
    /**
    -0.67
     referenties
    -0.66
    ViewFeatures
    -0.65
     հղումներ
    -0.63
    Při
    -0.60
    POSITIVE LOGITS
     Austin
    1.45
    Austin
    1.36
     AUSTIN
    1.32
    USTIN
    1.26
     austin
    1.25
     marte
    0.98
     Simult
    0.95
     Mâ
    0.95
    austin
    0.95
     Bén
    0.95
    Activations Density 0.049%

    No Known Activations