© 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. 4919
    Prev
    Next
    INDEX
    Explanations

    references to opting in or out of services, offers, or benefits

    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
    1271
    +0.13
    0.5%
    1335
    +0.13
    0.4%
    420
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1335
    +0.13
    0.02
    124
    +0.13
    0.02
    1271
    +0.11
    0.02
    Negative Logits
     amal
    -0.59
     fresa
    -0.57
     rú
    -0.54
     haus
    -0.51
     gesta
    -0.51
     tota
    -0.50
     Meny
    -0.49
    quarelle
    -0.48
     poc
    -0.47
     mantequilla
    -0.47
    POSITIVE LOGITS
     opt
    1.25
     opting
    1.22
     Opt
    1.15
     opted
    1.06
    opt
    1.01
     opts
    1.00
    Opt
    1.00
     hairc
    0.94
     disreg
    0.91
     cytoplas
    0.90
    Activations Density 0.053%

    No Known Activations