© 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. 2944
    Prev
    Next
    INDEX
    Explanations

    the word "Sarita"

    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
    1023
    +0.12
    0.4%
    120
    +0.09
    0.3%
    82
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.12
    0.03
    304
    +0.09
    0.01
    283
    +0.07
    0.01
    Negative Logits
    yao
    -0.59
    jorie
    -0.57
    structors
    -0.55
     weather
    -0.53
     through
    -0.53
     zupełnie
    -0.53
    squareup
    -0.53
     still
    -0.52
     herunter
    -0.52
     even
    -0.52
    POSITIVE LOGITS
    ita
    2.65
    ITA
    1.98
    itas
    1.60
     inder
    1.46
     rita
    1.43
     wien
    1.36
     fte
    1.35
     fta
    1.33
     dispen
    1.32
     effe
    1.31
    Activations Density 0.222%

    No Known Activations