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

    Neuronpedia

    Jacobian LensNEW
    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. 5876
    Prev
    Next
    INDEX
    Explanations

    words related to news events and current affairs

    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
    468
    +0.13
    0.4%
    950
    +0.09
    0.3%
    674
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    763
    +0.13
    0.04
    468
    +0.09
    0.04
    276
    +0.08
    0.03
    Negative Logits
     mitte
    -0.54
     sarili
    -0.53
     entraîne
    -0.53
     contribue
    -0.48
     kõik
    -0.48
     Geruch
    -0.45
     provoque
    -0.44
     NUKAT
    -0.43
    político
    -0.43
     dépasse
    -0.43
    POSITIVE LOGITS
    Whats
    0.63
    whats
    0.62
    ಊ
    0.60
     véritables
    0.56
    zbęd
    0.55
    ಔ
    0.55
    ?";
    0.54
    ಐ
    0.53
     noel
    0.53
     prisonniers
    0.53
    Activations Density 0.090%

    No Known Activations