© 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. 4760
    Prev
    Next
    INDEX
    Explanations

    mentions of conflict, disasters, and political situations

    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
    +0.12
    0.4%
    1343
    +0.11
    0.3%
    876
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.12
    0.04
    648
    +0.11
    0.02
    1770
    +0.10
    0.03
    Negative Logits
     Secrétaire
    -1.54
     vété
    -1.51
     confé
    -1.47
     vieill
    -1.36
     déplo
    -1.35
     clô
    -1.32
     écou
    -1.30
     flé
    -1.24
     éc
    -1.24
     malheureux
    -1.23
    POSITIVE LOGITS
     miscon
    0.74
     poteva
    0.73
     EMERG
    0.72
    Zgod
    0.68
     note
    0.65
     ineffec
    0.65
     flagrant
    0.65
     mis
    0.64
     salutary
    0.64
     special
    0.64
    Activations Density 0.299%

    No Known Activations