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. 660
    Prev
    Next
    INDEX
    Explanations

    instances of the article "a" and its variations in the text

    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
    +0.45
    2.3%
    1967
    +0.15
    0.8%
    1896
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.45
    0.11
    1896
    +0.15
    0.08
    1034
    +0.12
    0.07
    Negative Logits
    <bos>
    -2.19
    //};
    -0.66
    };*/
    -0.61
    //----
    -0.61
    //---
    -0.60
     confiable
    -0.60
    //});
    -0.59
     automáticamente
    -0.58
    ///**
    -0.56
    ⓧ
    -0.55
    POSITIVE LOGITS
     Haci
    0.91
     viciss
    0.86
     Compañ
    0.84
     valencia
    0.79
     quoique
    0.79
     véhic
    0.79
     conflic
    0.76
     sappi
    0.76
     hacienda
    0.75
     Áng
    0.74
    Activations Density 0.485%

    No Known Activations