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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 7059
    Prev
    Next
    INDEX
    Explanations

    prompts related to user engagement and participation on a website platform

    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
    +0.19
    1.2%
    1562
    +0.12
    0.7%
    478
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1562
    +0.19
    0.03
    537
    +0.12
    0.03
    1565
    +0.11
    0.02
    Negative Logits
    <bos>
    -3.40
    uxxxx
    -0.71
    public
    -0.71
    @
    -0.70
    //
    -0.67
    WriteLiteral
    -0.67
    CodeDom
    -0.67
    struct
    -0.66
    .
    -0.65
    ;
    -0.65
    POSITIVE LOGITS
     stockholm
    1.95
     swarovski
    1.92
     unlaw
    1.88
     eiffel
    1.87
     increa
    1.87
     affor
    1.84
     impra
    1.77
     sappi
    1.76
     wikihow
    1.76
     lidl
    1.75
    Activations Density 0.083%

    No Known Activations