© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 4463
    Prev
    Next
    INDEX
    Explanations

    phrases related to New York City and New York State

    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
    +0.12
    0.4%
    101
    +0.11
    0.4%
    506
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.12
    0.04
    1370
    +0.11
    0.05
    1777
    +0.11
    0.04
    Negative Logits
     aspetta
    -0.66
    isContained
    -0.65
    userdetails
    -0.62
     sento
    -0.62
     conosce
    -0.62
     broderie
    -0.60
    šech
    -0.60
     gilet
    -0.59
     rendono
    -0.59
     Ottobre
    -0.58
    POSITIVE LOGITS
     York
    1.14
     NY
    1.12
    York
    0.99
    NY
    0.99
     NYC
    0.90
     Ny
    0.85
     YORK
    0.83
     Yorkers
    0.79
    york
    0.76
    NYC
    0.76
    Activations Density 0.067%

    No Known Activations