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. 6129
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or professional practices

    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
    +0.17
    1.1%
    645
    +0.13
    0.8%
    732
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    645
    +0.17
    0.04
    1133
    +0.13
    0.04
    732
    +0.12
    0.03
    Negative Logits
    <bos>
    -3.43
    ⓧ
    -0.77
    <?
    
    -0.65
    //---
    -0.63
    displayquote
    -0.61
    /***
    
    -0.61
    /**
    
    -0.58
    protected
    -0.57
     bezeichneter
    -0.57
    /*++
    -0.56
    POSITIVE LOGITS
     impra
    1.32
     affor
    1.23
     maneu
    1.21
     Minang
    1.21
     stockholm
    1.21
     eiffel
    1.19
     wien
    1.19
     bandung
    1.19
     accla
    1.16
     increa
    1.16
    Activations Density 0.079%

    No Known Activations