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. 6134
    Prev
    Next
    INDEX
    Explanations

    quotes or philosophical statements

    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
    +0.31
    1.2%
    394
    +0.10
    0.4%
    1253
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1253
    +0.31
    0.04
    394
    +0.10
    0.11
    1744
    +0.08
    0.07
    Negative Logits
    <bos>
    -1.81
    hline
    -0.70
    public
    -0.70
    GroupLayout
    -0.69
    /**
    
    -0.69
    /*
    -0.67
    <tr>
    -0.65
    /**
    -0.64
    //
    -0.63
    </tbody>
    -0.62
    POSITIVE LOGITS
     swarovski
    1.44
     ricardo
    1.37
     impra
    1.37
     véhic
    1.36
     sergio
    1.36
     affor
    1.33
     hairc
    1.29
     embodi
    1.29
     philanth
    1.29
     carrefour
    1.29
    Activations Density 3.131%

    No Known Activations