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. 6057
    Prev
    Next
    INDEX
    Explanations

    mentions of specific technical details about vehicles, including model names, parts, and issues

    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
    +0.21
    0.8%
    1177
    +0.11
    0.4%
    227
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.21
    0.01
    1978
    +0.11
    0.08
    227
    +0.09
    0.08
    Negative Logits
    <bos>
    -2.51
    
    
    -1.37
    /**
    -1.25
     cabrio
    -1.25
    ⓧ
    -1.24
     isuzu
    -1.12
     chrysler
    -1.09
     skoda
    -1.08
    <?
    -1.07
     stihl
    -1.05
    POSITIVE LOGITS
     Muito
    0.73
     Qualquer
    0.71
     Quais
    0.70
     véhic
    0.69
     considér
    0.67
     genshin
    0.66
     vété
    0.65
     Tudo
    0.65
     Changelog
    0.65
     pym
    0.65
    Activations Density 0.980%

    No Known Activations