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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14011
    Prev
    Next
    INDEX
    Explanations

    details about a specific band's members and record labels

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1343
    +0.26
    0.8%
    776
    +0.15
    0.5%
    1967
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.26
    0.03
    353
    +0.15
    0.03
    1786
    +0.14
    0.01
    Negative Logits
     shenan
    -1.05
     apprehen
    -1.00
     gaily
    -0.93
     unspeak
    -0.88
     endeavouring
    -0.84
     Punj
    -0.83
     McLaugh
    -0.82
     disagre
    -0.81
     impelled
    -0.81
     reluct
    -0.80
    POSITIVE LOGITS
     تانيه
    0.80
     bonté
    0.77
     بيها
    0.70
     itali
    0.68
     dignité
    0.68
     espri
    0.66
     ↔
    0.66
     CURLOPT
    0.65
     charité
    0.64
     antici
    0.64
    Activations Density 0.081%

    No Known Activations