© 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. 7006
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to specific books, authors, and movies

    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
    1699
    +0.15
    0.4%
    478
    +0.14
    0.4%
    674
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    19
    +0.15
    0.05
    478
    +0.14
    0.04
    1902
    +0.13
    0.04
    Negative Logits
     a
    -0.65
     that
    -0.65
     because
    -0.63
     in
    -0.62
     though
    -0.62
     some
    -0.61
     up
    -0.61
     it
    -0.61
     her
    -0.61
    已经有
    -0.60
    POSITIVE LOGITS
     sopr
    1.50
     ordina
    1.47
     siff
    1.47
     ivi
    1.46
     alkoh
    1.46
     idr
    1.45
     istan
    1.45
     Settembre
    1.41
     italia
    1.37
     bont
    1.36
    Activations Density 0.163%

    No Known Activations