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. 6835
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial disclosures and business ownership

    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
    +0.24
    1.0%
    381
    +0.12
    0.5%
    382
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    645
    +0.24
    0.07
    289
    +0.12
    0.07
    172
    +0.09
    0.07
    Negative Logits
    <bos>
    -2.40
    /***
    
    -0.94
     intersper
    -0.90
     endow
    -0.83
    ⓧ
    -0.83
     disbur
    -0.73
     inaugurate
    -0.71
    //---
    -0.69
    ///**
    -0.69
     enshr
    -0.68
    POSITIVE LOGITS
     cioc
    0.80
     régal
    0.70
     écout
    0.68
    Also
    0.67
     [{
    
    0.67
    mistak
    0.67
     Also
    0.66
     dégust
    0.65
    also
    0.64
     ALSO
    0.63
    Activations Density 0.945%

    No Known Activations