Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15196
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS related terms

    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
    492
    +0.15
    0.7%
    486
    +0.14
    0.7%
    390
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1741
    +0.15
    -0.00
    227
    +0.14
    0.06
    1343
    +0.13
    0.06
    Negative Logits
    ⓧ
    -0.72
     auton
    -0.66
    atguigu
    -0.65
     notor
    -0.64
     Bertram
    -0.63
     Erlangen
    -0.63
     Abbé
    -0.62
     pessi
    -0.62
     Tübingen
    -0.60
     soigne
    -0.59
    POSITIVE LOGITS
    css
    0.94
     Sty
    0.94
    CSS
    0.93
     CSS
    0.91
     css
    0.91
    Sty
    0.87
    Css
    0.83
     sty
    0.72
     prič
    0.69
     stylist
    0.65
    Activations Density 0.583%

    No Known Activations