© 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. 0-RES-JB
    11. 2759
    Prev
    Next
    INDEX
    Explanations

    references to a specific person named Rex Mitchell

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    1909
    +0.09
    0.3%
    442
    +0.09
    0.3%
    1045
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.09
    0.06
    1363
    +0.09
    0.04
    1120
    +0.07
    0.04
    Negative Logits
     acacia
    -0.64
     WALTZ
    -0.64
     lycra
    -0.63
     COPPER
    -0.63
     sherpa
    -0.62
     organza
    -0.62
     ROGER
    -0.62
     kraken
    -0.62
     tawny
    -0.61
     zelda
    -0.60
    POSITIVE LOGITS
     Rex
    1.25
    bn
    1.24
     Sund
    1.20
    Rex
    1.15
    Sund
    1.09
     sund
    0.95
     Rox
    0.95
    Rox
    0.86
     BIBSYS
    0.85
     Mog
    0.81
    Activations Density 0.304%

    No Known Activations