© 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. 5141
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hum" and its variations, indicating a focus on humor or light-heartedness

    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
    1325
    +0.17
    0.9%
    1406
    +0.14
    0.8%
    1034
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.17
    0.02
    347
    +0.14
    0.02
    1325
    +0.13
    0.02
    Negative Logits
    <bos>
    -1.31
    glBegin
    -0.56
    لينكات
    -0.52
    Бан
    -0.50
    벳
    -0.50
    contentLoaded
    -0.49
    ⓧ
    -0.49
    стьян
    -0.49
    -0.49
    AddWithValue
    -0.48
    POSITIVE LOGITS
     Hum
    1.47
    Hum
    1.39
     HUM
    1.28
     hum
    1.27
     Hummel
    1.19
    HUM
    1.17
    hum
    1.12
     Humph
    1.00
     humus
    0.98
     humming
    0.96
    Activations Density 0.147%

    No Known Activations