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. 13592
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations, especially in Brooklyn

    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
    90
    +0.14
    0.5%
    1741
    +0.12
    0.5%
    732
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1971
    +0.14
    0.02
    1965
    +0.12
    0.02
    1537
    +0.11
    0.02
    Negative Logits
    ाहरण
    -0.70
    SequentialGroup
    -0.65
    resave
    -0.62
    PerformLayout
    -0.60
    ParallelGroup
    -0.59
     PeEnEo
    -0.57
    userdetails
    -0.57
    XmlAccessType
    -0.57
    dreamstime
    -0.57
     referenties
    -0.56
    POSITIVE LOGITS
     Brooklyn
    1.36
    Brooklyn
    1.25
     brooklyn
    1.22
     Souha
    0.91
     pavillon
    0.89
     Ibidem
    0.82
     Traité
    0.81
     Benoît
    0.79
     Marín
    0.79
     Gorb
    0.78
    Activations Density 0.091%

    No Known Activations