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. 1069
    Prev
    Next
    INDEX
    Explanations

    names of athletes and associated performance metrics

    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
    1343
    +0.19
    0.7%
    1177
    +0.15
    0.5%
    381
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.19
    0.09
    981
    +0.15
    0.08
    1177
    +0.14
    0.02
    Negative Logits
    <bos>
    -1.76
    ,
    -0.75
     and
    -0.72
     or
    -0.71
     vorhandenen
    -0.70
     erforderlichen
    -0.70
    .
    -0.69
     Wirkungen
    -0.68
     Rücksicht
    -0.68
    ↵
    -0.67
    POSITIVE LOGITS
     keramik
    1.73
     Kategor
    1.68
     mikrofon
    1.66
     karton
    1.66
     kram
    1.65
     alkoh
    1.63
     silikon
    1.59
     kosme
    1.56
     quoique
    1.51
     ciga
    1.50
    Activations Density 0.305%

    No Known Activations