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. 1826
    Prev
    Next
    INDEX
    Explanations

    dates and their respective formats

    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
    +0.33
    1.4%
    1351
    +0.09
    0.4%
    776
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.33
    0.08
    1267
    +0.09
    0.07
    1324
    +0.09
    0.07
    Negative Logits
    <bos>
    -2.70
     jsPsych
    -0.70
     "..\..\..\
    -0.70
     hefyd
    -0.69
    ništvo
    -0.68
    AccessorTable
    -0.67
    énario
    -0.67
     gynnwys
    -0.67
     povezave
    -0.66
    šech
    -0.64
    POSITIVE LOGITS
     maneu
    2.00
     reluct
    1.93
     impra
    1.82
     disagre
    1.79
     shenan
    1.71
     affor
    1.70
     accla
    1.66
     increa
    1.64
     disgra
    1.63
     apprehen
    1.62
    Activations Density 0.245%

    No Known Activations