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. 3108
    Prev
    Next
    INDEX
    Explanations

    mentions of South American countries and related political and economic events

    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
    2004
    +0.13
    0.4%
    1103
    +0.10
    0.3%
    805
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.13
    0.04
    512
    +0.10
    0.04
    973
    +0.10
    0.03
    Negative Logits
     Áng
    -1.78
     Lázaro
    -1.66
     Compañ
    -1.65
     Darío
    -1.59
     Cár
    -1.58
     Bahía
    -1.54
     Valentín
    -1.49
     Belén
    -1.49
     Alcalde
    -1.47
     Asunción
    -1.40
    POSITIVE LOGITS
     Aner
    1.05
     Thier
    1.04
     Middles
    1.04
     Leyden
    0.97
     Inhabitants
    0.96
     Sted
    0.96
     Vaugh
    0.95
     Seel
    0.93
     Tole
    0.92
     Glou
    0.91
    Activations Density 0.138%

    No Known Activations