© 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 EvalsExportsinterp-engineNEWAPI 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. 4908
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events and news

    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
    2019
    +0.36
    1.2%
    1535
    +0.20
    0.7%
    381
    +0.19
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.36
    0.04
    1535
    +0.20
    0.03
    946
    +0.19
    0.03
    Negative Logits
    Dlaczego
    -0.77
    Și
    -0.75
    Może
    -0.73
    Gdzie
    -0.70
    Să
    -0.70
    Czym
    -0.68
    Natürlich
    -0.66
    Genau
    -0.65
    Jakie
    -0.65
    Conheça
    -0.65
    POSITIVE LOGITS
     reluct
    1.31
     Keny
    1.30
     Juf
    1.29
     fta
    1.27
     accla
    1.26
     embra
    1.25
     istan
    1.24
     Intere
    1.23
     philanth
    1.21
     Augu
    1.21
    Activations Density 0.047%

    No Known Activations