Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8265
    Prev
    Next
    INDEX
    Explanations

    mentions of legal proceedings and governmental actions, specifically focusing on hearings, testimonies, and intelligence committees

    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
    453
    +0.10
    0.3%
    752
    +0.09
    0.3%
    856
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.10
    0.05
    1499
    +0.09
    0.04
    453
    +0.08
    0.04
    Negative Logits
     purée
    -0.62
     nutella
    -0.51
     gliss
    -0.49
     COMMUNIC
    -0.48
     BEHAV
    -0.48
     upvoted
    -0.48
     EXERCISES
    -0.48
     bleeds
    -0.48
     buttercream
    -0.47
    Rgds
    -0.47
    POSITIVE LOGITS
     gouver
    0.75
     alkoh
    0.75
    principalColumn
    0.70
     déliv
    0.69
     kompati
    0.67
     évalu
    0.65
     dör
    0.65
     rémun
    0.65
     Nö
    0.62
     karton
    0.62
    Activations Density 0.273%

    No Known Activations