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. 935
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically commas

    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
    +0.23
    1.0%
    382
    +0.14
    0.6%
    1331
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.23
    0.04
    1331
    +0.14
    0.04
    229
    +0.11
    0.04
    Negative Logits
    <bos>
    -2.57
    ⓧ
    -0.93
    },[])
    -0.72
     inaugurate
    -0.70
     intersper
    -0.68
    
    
    -0.66
     ratify
    -0.64
    <?
    -0.64
     endow
    -0.63
     supersede
    -0.63
    POSITIVE LOGITS
     bandung
    0.97
     multicolore
    0.95
     tibi
    0.92
     cioc
    0.92
     Luglio
    0.91
     cæ
    0.90
     Giugno
    0.90
     sirop
    0.89
     Portugu
    0.88
     Gestão
    0.87
    Activations Density 0.056%

    No Known Activations