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. 828
    Prev
    Next
    INDEX
    Explanations

    the term "rush" and its variations in different contexts

    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
    +0.18
    1.0%
    555
    +0.15
    0.9%
    1272
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.18
    0.02
    1272
    +0.15
    0.02
    397
    +0.13
    0.02
    Negative Logits
    <bos>
    -2.50
    /***
    
    -0.77
    glEnd
    -0.70
    },{
    
    -0.69
    alignSelf
    -0.67
    marginHorizontal
    -0.67
    SourceChecksum
    -0.66
    VIAF
    -0.65
    module
    -0.65
    |}
    -0.64
    POSITIVE LOGITS
     affor
    1.46
     scrat
    1.37
     unden
    1.35
     increa
    1.33
     strick
    1.33
     swarovski
    1.32
     jurassic
    1.31
     casio
    1.31
     unce
    1.30
     madonna
    1.29
    Activations Density 0.056%

    No Known Activations