© 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. 4330
    Prev
    Next
    INDEX
    Explanations

    occurrences of legal terms or terms related to formal agreements and procedures

    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
    1438
    +0.08
    0.2%
    61
    +0.08
    0.2%
    939
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1438
    +0.08
    0.02
    341
    +0.08
    0.03
    1278
    +0.08
    0.03
    Negative Logits
    ButterKnife
    -0.45
    QSize
    -0.41
    GOTREF
    -0.40
     snippetHide
    -0.40
     Galle
    -0.40
    ü
    -0.40
    BlockingQueue
    -0.40
    YUV
    -0.39
    X
    -0.39
     nearly
    -0.39
    POSITIVE LOGITS
     hairc
    0.88
     hoody
    0.86
     véhic
    0.81
     ftre
    0.79
     perfon
    0.77
     paillettes
    0.76
     renforcé
    0.76
     fhould
    0.73
     Krzysz
    0.73
     occafion
    0.73
    Activations Density 0.172%

    No Known Activations