© 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. 4915
    Prev
    Next
    INDEX
    Explanations

    references to the Environmental Protection Agency (EPA)

    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
    +0.16
    0.8%
    1387
    +0.13
    0.7%
    31
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1387
    +0.16
    0.02
    1983
    +0.13
    0.01
    31
    +0.13
    0.01
    Negative Logits
    <bos>
    -2.20
    /**
    -0.85
    ⓧ
    -0.73
    
    -0.67
    <?
    -0.66
    <?
    -0.65
    Бере
    -0.61
    Kontrola
    -0.60
    Ży
    -0.59
    حياته
    -0.57
    POSITIVE LOGITS
     EPA
    1.13
    EPA
    1.08
     Præ
    1.08
     Minang
    1.06
     epa
    1.05
     Græ
    1.04
     Hæ
    1.02
     bandung
    0.99
     Muhamma
    0.98
     cæ
    0.98
    Activations Density 0.048%

    No Known Activations