© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 2651
    Prev
    Next
    INDEX
    Explanations

    details about demographics, such as household size, income, and household members

    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
    241
    +0.15
    0.7%
    1381
    +0.13
    0.6%
    1065
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1381
    +0.15
    0.02
    1793
    +0.13
    0.02
    1065
    +0.12
    0.02
    Negative Logits
    <bos>
    -1.75
    
    -0.87
    /***
    -0.76
    ⓧ
    -0.74
    <?
    -0.66
    /**
    -0.65
    <?
    -0.64
    LinkedHashMap
    -0.61
    BufferedWriter
    -0.57
    <!--
    -0.56
    POSITIVE LOGITS
    Household
    1.43
     Household
    1.42
     household
    1.40
    household
    1.30
     Households
    1.30
     milano
    1.17
     napoli
    1.13
     households
    1.11
     tanga
    1.07
     lele
    1.07
    Activations Density 0.271%

    No Known Activations