© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6048
    Prev
    Next
    INDEX
    Explanations

    terms related to drinks and beverages, specifically focusing on whiskey and bourbon

    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
    370
    +0.11
    0.4%
    1437
    +0.10
    0.3%
    1798
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1798
    +0.11
    0.03
    507
    +0.10
    0.03
    1935
    +0.10
    0.02
    Negative Logits
     karton
    -0.68
     akus
    -0.66
     ideolog
    -0.65
     kosme
    -0.65
     silikon
    -0.64
     biograf
    -0.64
     hek
    -0.63
     Konkur
    -0.63
     minimalis
    -0.62
     spion
    -0.62
    POSITIVE LOGITS
     whiskey
    1.00
     distillery
    0.91
     Whiskey
    0.85
    whiskey
    0.83
     cocktails
    0.83
     distill
    0.83
     whisky
    0.83
     liquor
    0.79
     cocktail
    0.79
     booze
    0.77
    Activations Density 0.094%

    No Known Activations