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. 3023
    Prev
    Next
    INDEX
    Explanations

    political and geographical terms related to regions and international relations

    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
    906
    +0.10
    0.3%
    1343
    +0.10
    0.3%
    609
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.10
    0.04
    609
    +0.10
    0.03
    1511
    +0.09
    0.01
    Negative Logits
     لينك
    -0.53
    forChild
    -0.49
    ("]");
    -0.47
    (',');
    -0.46
    ={`/
    -0.46
     growled
    -0.45
     będę
    -0.45
    (")");
    -0.44
    (",");
    -0.44
     jerked
    -0.43
    POSITIVE LOGITS
     ftu
    0.70
     laft
    0.68
     meuble
    0.68
     fup
    0.65
     nuage
    0.65
     cimetière
    0.63
     pavillon
    0.63
     tranf
    0.63
     accessoire
    0.63
     vœ
    0.63
    Activations Density 0.178%

    No Known Activations