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. 8917
    Prev
    Next
    INDEX
    Explanations

    a mix of technical terms, personal anecdotes, and emotional expressions

    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
    +0.21
    0.9%
    1473
    +0.11
    0.5%
    381
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1473
    +0.21
    0.11
    605
    +0.11
    0.02
    1965
    +0.09
    0.08
    Negative Logits
    <bos>
    -2.57
    /***
    
    -0.76
    ///**
    -0.75
    octanol
    -0.70
    HasAnnotation
    -0.65
    CreateMap
    -0.65
    //---
    -0.65
     intptr
    -0.65
    addGroup
    -0.64
        
    -0.64
    POSITIVE LOGITS
     unlaw
    1.92
     maneu
    1.88
     reluct
    1.73
     impractica
    1.71
     disagre
    1.69
     affor
    1.68
     increa
    1.67
     shenan
    1.67
     accla
    1.64
     depic
    1.63
    Activations Density 3.261%

    No Known Activations