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. 569
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics, international relations, and governmental activities

    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
    1643
    +0.09
    0.3%
    674
    +0.08
    0.2%
    642
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1165
    +0.09
    0.02
    408
    +0.08
    0.03
    713
    +0.07
    0.03
    Negative Logits
     increa
    -1.59
     affor
    -1.59
     unspeak
    -1.52
     impra
    -1.51
     shenan
    -1.50
     scrat
    -1.50
     disreg
    -1.48
     suscep
    -1.46
     encomp
    -1.45
     guarante
    -1.44
    POSITIVE LOGITS
     NSCoder
    0.64
    gbaar
    0.62
    batore
    0.62
     amid
    0.62
    phosa
    0.61
    riwal
    0.59
    copg
    0.58
    Conclusión
    0.58
     desertcart
    0.57
     Wikispecies
    0.56
    Activations Density 0.122%

    No Known Activations