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. 1166
    Prev
    Next
    INDEX
    Explanations

    capitalized 'S' indicating significant or starting points in sentences

    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
    +0.27
    1.7%
    667
    +0.15
    0.9%
    1276
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    667
    +0.27
    0.05
    442
    +0.15
    0.03
    1142
    +0.11
    0.03
    Negative Logits
    <bos>
    -3.20
    ⓧ
    -1.11
    otheby
    -0.85
    underland
    -0.78
    criptures
    -0.71
    /*---
    -0.70
     establish
    -0.70
    USTAIN
    -0.70
    couts
    -0.70
    /*
    -0.68
    POSITIVE LOGITS
     increa
    1.57
     impra
    1.56
     unlaw
    1.55
     lele
    1.53
     aen
    1.53
     Keny
    1.51
     affor
    1.48
     Juf
    1.48
     Minang
    1.46
     compréhen
    1.44
    Activations Density 0.049%

    No Known Activations