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. 649
    Prev
    Next
    INDEX
    Explanations

    phrases, words, and concepts related to cooking mistakes

    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
    +0.17
    0.9%
    161
    +0.10
    0.5%
    1548
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1601
    +0.17
    0.03
    1363
    +0.10
    0.03
    36
    +0.10
    0.03
    Negative Logits
    <bos>
    -3.61
    public
    -0.75
        
    -0.72
    enumerate
    -0.71
    foreach
    -0.70
    struct
    -0.70
     provide
    -0.70
     look
    -0.70
    <eos>
    -0.70
    echo
    -0.69
    POSITIVE LOGITS
     stockholm
    2.17
     Minang
    2.11
     bandung
    2.00
     Juf
    1.98
     aen
    1.94
     lele
    1.93
     fta
    1.93
     wien
    1.92
     mef
    1.92
     meis
    1.91
    Activations Density 0.109%

    No Known Activations