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. 9116
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to terms and conditions, agreements, and permissions

    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
    +0.20
    0.9%
    1013
    +0.12
    0.6%
    1984
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.20
    0.20
    1658
    +0.12
    0.11
    1166
    +0.09
    0.10
    Negative Logits
    <bos>
    -3.52
    /***
    
    -1.06
    /*!
    
    -0.80
    endwhile
    -0.77
    //---
    -0.76
     intersper
    -0.73
     amass
    -0.72
    ⓧ
    -0.71
     disbur
    -0.70
    
    
    -0.69
    POSITIVE LOGITS
     pymysql
    0.89
    °;
    0.87
     bandung
    0.81
    GYPT
    0.81
     ecru
    0.80
     africain
    0.80
     bagay
    0.79
     silikon
    0.79
     sarili
    0.79
     stockholm
    0.78
    Activations Density 5.114%

    No Known Activations