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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 388
    Prev
    Next
    INDEX
    Explanations

    mentions or references to places or entities related to Kentucky

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    370
    +0.15
    0.8%
    1757
    +0.14
    0.7%
    900
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.15
    0.05
    648
    +0.14
    0.04
    900
    +0.14
    0.04
    Negative Logits
    <bos>
    -1.61
     quitted
    -0.79
     shewn
    -0.76
     endeavoured
    -0.76
    
    
    -0.75
    ⓧ
    -0.75
    CreateMap
    -0.72
     endow
    -0.67
    /***
    
    -0.67
     emigrated
    -0.67
    POSITIVE LOGITS
     Kentucky
    1.38
    Kentucky
    1.34
     Ky
    1.25
     KY
    1.23
    Ky
    1.13
     ky
    1.07
     Louisville
    1.03
    Louisville
    0.92
    Lexington
    0.89
     KENT
    0.88
    Activations Density 0.516%

    No Known Activations