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. 15688
    Prev
    Next
    INDEX
    Explanations

    Japanese names, locations, and organizations

    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
    924
    +0.09
    0.3%
    1677
    +0.08
    0.2%
    227
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.09
    0.06
    227
    +0.08
    0.06
    143
    +0.08
    0.05
    Negative Logits
     affez
    -0.76
     mosso
    -0.69
     ovunque
    -0.65
     kaka
    -0.61
     migli
    -0.61
     biar
    -0.60
     Tahu
    -0.60
     apparti
    -0.60
     nuoc
    -0.60
     kule
    -0.60
    POSITIVE LOGITS
     McLaugh
    0.88
     sophistic
    0.86
     unspeak
    0.75
     gaily
    0.73
     beaute
    0.72
     apprehen
    0.70
     madonna
    0.69
     snoopy
    0.69
     emphat
    0.69
     Machia
    0.68
    Activations Density 0.274%

    No Known Activations