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. 901
    Prev
    Next
    INDEX
    Explanations

    alternative options or solutions to a given situation or problem

    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
    +0.18
    1.0%
    1323
    +0.11
    0.6%
    32
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1323
    +0.18
    0.02
    1865
    +0.11
    0.02
    32
    +0.10
    0.02
    Negative Logits
    <bos>
    -3.27
    
    
    -0.77
    /***
    
    -0.68
    //@
    -0.68
    //---
    -0.67
    BUYER
    -0.66
    /*!
    
    -0.65
    const
    -0.65
    show
    -0.64
    cout
    -0.64
    POSITIVE LOGITS
     fta
    1.83
     lele
    1.83
     stockholm
    1.80
     jaya
    1.78
     aen
    1.77
     Juf
    1.74
     affor
    1.73
     hcm
    1.72
     ftu
    1.72
     fortn
    1.70
    Activations Density 0.063%

    No Known Activations