© 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. 4823
    Prev
    Next
    INDEX
    Explanations

    references to martial arts and related terms

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    732
    +0.13
    0.6%
    1124
    +0.12
    0.6%
    411
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.13
    0.03
    1910
    +0.12
    0.02
    227
    +0.12
    0.03
    Negative Logits
    <bos>
    -1.72
     kani
    -0.68
     pama
    -0.67
    qiao
    -0.67
    ValueGeneration
    -0.66
     karna
    -0.63
    IConfiguration
    -0.60
     cek
    -0.60
    guang
    -0.59
     muna
    -0.57
    POSITIVE LOGITS
     martial
    1.15
    Martial
    1.14
     impra
    1.09
     Martial
    1.09
     unspeak
    1.06
     McInt
    1.01
     affor
    0.96
     ecru
    0.96
    martial
    0.94
     marl
    0.94
    Activations Density 0.127%

    No Known Activations