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

    Neuronpedia

    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. 12276
    Prev
    Next
    INDEX
    Explanations

    phrases related to alcohol levels, blood alcohol content, and driving penalties

    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
    946
    +0.11
    0.3%
    1553
    +0.09
    0.3%
    970
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.11
    0.03
    1553
    +0.09
    0.03
    972
    +0.08
    0.02
    Negative Logits
     intrig
    -0.55
     tibi
    -0.44
     tenda
    -0.43
     quæ
    -0.42
     ejus
    -0.41
     trasferimento
    -0.41
     utop
    -0.41
     ruine
    -0.41
     vinci
    -0.41
     vola
    -0.40
    POSITIVE LOGITS
     intoxication
    0.57
     drunkenness
    0.56
     alcohol
    0.53
     intoxicated
    0.51
     drunk
    0.48
     DUI
    0.47
     drowsiness
    0.46
     impairment
    0.46
     drunken
    0.46
     kumar
    0.46
    Activations Density 0.171%

    No Known Activations