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. 227
    Prev
    Next
    INDEX
    Explanations

    statistical or numerical information, such as rankings, figures, and percentages

    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
    1042
    +0.10
    0.3%
    674
    +0.07
    0.2%
    1562
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1834
    +0.10
    0.03
    838
    +0.07
    0.03
    2012
    +0.07
    0.03
    Negative Logits
     ohr
    -1.02
     hina
    -1.01
     „,
    -0.95
     adal
    -0.94
     lele
    -0.93
     idr
    -0.93
     myn
    -0.91
     saar
    -0.89
     mef
    -0.89
     fup
    -0.89
    POSITIVE LOGITS
    <bos>
    0.85
     longest
    0.64
     smallest
    0.64
     largest
    0.63
     oldest
    0.60
     highest
    0.60
     tallest
    0.58
     second
    0.56
     lowest
    0.56
     busiest
    0.56
    Activations Density 0.107%

    No Known Activations