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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13904
    Prev
    Next
    INDEX
    Explanations

    words related to the circus, including themes, costumes, trainers, elephants, spotlights, travelers, and comedy

    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
    783
    +0.16
    0.5%
    994
    +0.16
    0.5%
    678
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.16
    0.04
    994
    +0.16
    0.04
    678
    +0.11
    0.04
    Negative Logits
    Solución
    -0.72
    🕗
    -0.67
     siff
    -0.64
     vache
    -0.63
     canne
    -0.63
     tén
    -0.62
     broderie
    -0.61
     vété
    -0.60
     broder
    -0.57
     fusil
    -0.57
    POSITIVE LOGITS
     circus
    0.76
     Paleozoic
    0.73
     Carboniferous
    0.72
     Silurian
    0.68
     limestones
    0.67
     Ordovician
    0.67
    circus
    0.66
     spectacle
    0.66
     Mesozoic
    0.64
     liberality
    0.62
    Activations Density 0.331%

    No Known Activations