© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4927
    Prev
    Next
    INDEX
    Explanations

    descriptions of individuals, particularly in the context of opinions and evaluations of their actions or characteristics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.34
    1.3%
    507
    +0.06
    0.2%
    9
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.34
    0.04
    715
    +0.06
    0.03
    513
    +0.06
    0.04
    Negative Logits
    <bos>
    -2.24
    /***
    -0.63
    ///**
    -0.60
    //};
    -0.60
    public
    -0.55
    this
    -0.55
    log
    -0.52
    else
    -0.51
    DataAnnotations
    -0.50
    |}
    -0.49
    POSITIVE LOGITS
     lamborghini
    1.11
     camry
    1.05
     hilux
    1.03
     swarovski
    1.02
     tupperware
    1.00
     ecru
    0.98
     chrysler
    0.98
     mitsubishi
    0.97
     paradiso
    0.95
     husqvarna
    0.95
    Activations Density 0.769%

    No Known Activations