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. 8903
    Prev
    Next
    INDEX
    Explanations

    ingredients from food recipes related to baking or cooking

    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
    1565
    +0.14
    0.8%
    50
    +0.14
    0.8%
    1350
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1565
    +0.14
    0.03
    1350
    +0.14
    0.02
    1256
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.93
    ⓧ
    -0.68
    ‏‏
    -0.64
    /*++
    -0.64
    CodeDom
    -0.64
     GenerationType
    -0.64
    /**
    -0.62
        
    -0.62
    HasIndex
    -0.60
    KURZBESCHREIBUNG
    -0.60
    POSITIVE LOGITS
     maroc
    1.36
     Butter
    1.31
     butter
    1.29
     BUTTER
    1.26
     Juf
    1.25
     vne
    1.23
    Butter
    1.23
    butter
    1.19
     quoc
    1.18
     lele
    1.15
    Activations Density 0.142%

    No Known Activations