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. 14869
    Prev
    Next
    INDEX
    Explanations

    geographical locations, specifically focusing on the Eastern region

    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
    50
    +0.12
    0.7%
    889
    +0.11
    0.6%
    1334
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1805
    +0.12
    0.03
    200
    +0.11
    0.03
    1512
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.46
    ⓧ
    -0.82
    /**
    -0.77
    /*
    -0.75
    //});
    -0.73
    CreateMap
    -0.72
    /*---
    -0.71
    ///**
    -0.70
    RUnlock
    -0.69
    /***
    
    -0.67
    POSITIVE LOGITS
     milf
    1.51
     jorge
    1.38
     madonna
    1.37
     Juf
    1.32
     shenan
    1.31
     Augu
    1.31
     accla
    1.31
     disagre
    1.30
     perfet
    1.30
     excru
    1.30
    Activations Density 0.146%

    No Known Activations