© 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. 14775
    Prev
    Next
    INDEX
    Explanations

    references to articles from "The New York Times"

    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
    1741
    +0.15
    0.4%
    1013
    +0.09
    0.3%
    781
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1997
    +0.15
    0.04
    1992
    +0.09
    0.03
    613
    +0.09
    0.03
    Negative Logits
     ftu
    -1.57
     §.
    -1.51
     broderie
    -1.50
     fta
    -1.49
     »>
    -1.46
     aen
    -1.45
     aquarelle
    -1.45
     wien
    -1.44
     matel
    -1.44
     tranf
    -1.43
    POSITIVE LOGITS
     Times
    0.93
    Times
    0.87
     newspaper
    0.78
    ’
    0.68
    times
    0.67
    nytimes
    0.66
     paper
    0.66
     News
    0.64
    '
    0.63
    TIMES
    0.62
    Activations Density 0.090%

    No Known Activations