© 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. 16341
    Prev
    Next
    INDEX
    Explanations

    words related to teamwork and collaboration

    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
    198
    +0.16
    0.5%
    50
    +0.12
    0.4%
    394
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.16
    0.06
    50
    +0.12
    0.05
    1728
    +0.09
    0.04
    Negative Logits
     vété
    -1.24
     alliés
    -1.21
     bénévoles
    -1.02
     spécialistes
    -1.02
     pères
    -1.00
     ouvriers
    -0.98
     milf
    -0.95
     créateur
    -0.95
     journalistes
    -0.94
     maneu
    -0.90
    POSITIVE LOGITS
     PLWABN
    0.67
     tumba
    0.63
     artists
    0.61
     guardia
    0.61
     parrilla
    0.61
     grans
    0.60
     незавершена
    0.59
     cabaña
    0.58
     designers
    0.58
     writers
    0.57
    Activations Density 0.380%

    No Known Activations