© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7025
    Prev
    Next
    INDEX
    Explanations

    references to flavors or tastes

    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
    1482
    +0.18
    0.6%
    1839
    +0.13
    0.5%
    1145
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1482
    +0.18
    0.03
    1839
    +0.13
    0.02
    75
    +0.11
    0.01
    Negative Logits
     parma
    -0.63
    Yogurt
    -0.62
     Zucchini
    -0.62
     Câ
    -0.61
     Perla
    -0.61
     Châ
    -0.60
     Ouv
    -0.60
     coq
    -0.60
     Portail
    -0.59
     Siria
    -0.58
    POSITIVE LOGITS
     taste
    1.33
    taste
    1.16
     tastes
    1.10
     Taste
    1.09
    Taste
    1.08
     tasted
    1.07
     tasting
    0.97
    tasting
    0.92
     tast
    0.89
     smak
    0.75
    Activations Density 0.061%

    No Known Activations