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. 1447
    Prev
    Next
    INDEX
    Explanations

    phrases related to government, constitutional rights, and political figures

    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
    478
    +0.13
    0.4%
    1385
    +0.11
    0.4%
    1937
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    131
    +0.13
    0.05
    1937
    +0.11
    0.06
    421
    +0.11
    0.05
    Negative Logits
     impra
    -0.91
     maneu
    -0.87
     inappro
    -0.83
     erad
    -0.76
     disagre
    -0.76
     unve
    -0.75
     vété
    -0.74
     noël
    -0.73
     madonna
    -0.73
     affor
    -0.72
    POSITIVE LOGITS
     our
    0.98
     Our
    0.96
    our
    0.96
    Our
    0.94
     ourselves
    0.87
     OUR
    0.85
    OUR
    0.83
     own
    0.77
     ours
    0.70
    我们的
    0.67
    Activations Density 0.140%

    No Known Activations