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. 3008
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, specifically Toronto and associated entities

    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
    200
    +0.15
    0.5%
    920
    +0.13
    0.4%
    1023
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.15
    0.03
    489
    +0.13
    0.03
    920
    +0.13
    0.02
    Negative Logits
     câte
    -0.62
     يتيمه
    -0.58
    ագրություններ
    -0.55
     Și
    -0.54
    Și
    -0.53
     հղումներ
    -0.50
    Może
    -0.50
    Vezi
    -0.50
     păr
    -0.49
    Bardzo
    -0.48
    POSITIVE LOGITS
     Toronto
    1.40
    Toronto
    1.29
    toronto
    1.01
     TORONTO
    0.97
     Canadian
    0.96
     Ontario
    0.95
     Canada
    0.91
     Canadians
    0.91
     toronto
    0.89
     Canadá
    0.87
    Activations Density 0.044%

    No Known Activations