© 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. 5057
    Prev
    Next
    INDEX
    Explanations

    notable names or entities in the context of media or 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
    1177
    +0.14
    0.4%
    577
    +0.10
    0.3%
    1965
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.14
    0.10
    577
    +0.10
    0.07
    1177
    +0.09
    0.04
    Negative Logits
     far
    -0.54
    并在
    -0.54
    верное
    -0.54
    并将
    -0.53
     번째
    -0.53
     but
    -0.53
    以及
    -0.53
    шкина
    -0.53
    Premio
    -0.52
    Попис
    -0.52
    POSITIVE LOGITS
     emphat
    1.85
     accla
    1.82
     wien
    1.71
     fta
    1.70
     casio
    1.69
     madonna
    1.69
     reluct
    1.68
     mef
    1.68
     depic
    1.65
     suspic
    1.65
    Activations Density 0.629%

    No Known Activations