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. 8412
    Prev
    Next
    INDEX
    Explanations

    locations in Manhattan

    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
    805
    +0.12
    0.4%
    897
    +0.10
    0.3%
    1052
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.12
    0.04
    227
    +0.10
    0.05
    438
    +0.10
    0.05
    Negative Logits
     Ottobre
    -0.81
    šech
    -0.70
     sappi
    -0.67
     affez
    -0.66
     exé
    -0.65
     brille
    -0.64
     Luglio
    -0.63
     soggior
    -0.62
     Giugno
    -0.62
     letti
    -0.62
    POSITIVE LOGITS
     NYC
    1.19
     Manhattan
    1.04
    NYC
    1.01
     NY
    1.00
     NYPD
    0.97
     Brooklyn
    0.94
    NY
    0.93
     nyc
    0.91
     Bronx
    0.91
    nyc
    0.90
    Activations Density 0.262%

    No Known Activations