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. 946
    Prev
    Next
    INDEX
    Explanations

    information related to tanning, bronzer, and skin care products

    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
    1602
    +0.16
    0.9%
    404
    +0.16
    0.8%
    479
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1763
    +0.16
    0.03
    1971
    +0.16
    0.03
    404
    +0.14
    0.03
    Negative Logits
    <bos>
    -1.21
     MCS
    -0.54
     gug
    -0.54
     Sheppard
    -0.54
     getNombre
    -0.53
     Brito
    -0.52
    /***
    
    -0.51
     Puli
    -0.50
     Opus
    -0.50
     Benav
    -0.48
    POSITIVE LOGITS
     Tan
    1.52
     tan
    1.50
    Tan
    1.44
    tan
    1.20
     TAN
    1.19
     tanning
    1.08
    TAN
    0.98
     tanned
    0.93
     Tanja
    0.80
     tans
    0.79
    Activations Density 0.357%

    No Known Activations