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. 889
    Prev
    Next
    INDEX
    Explanations

    the letter 's' in various contexts

    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
    +0.24
    0.8%
    131
    +0.07
    0.2%
    251
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1454
    +0.24
    0.06
    473
    +0.07
    0.07
    42
    +0.07
    0.07
    Negative Logits
    <bos>
    -1.59
    させていただきます
    -0.68
    ω
    -0.68
    α
    -0.64
     أيضًا
    -0.64
     защото
    -0.64
    〈
    -0.64
    —
    -0.64
    日
    -0.63
    govine
    -0.63
    POSITIVE LOGITS
     reluct
    1.93
     accla
    1.85
     disagre
    1.80
     indestru
    1.79
     maneu
    1.74
     shenan
    1.73
     impra
    1.70
     apprehen
    1.70
     increa
    1.68
     unspeak
    1.68
    Activations Density 1.468%

    No Known Activations