© 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. 5004
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases that indicate incremental processes or actions

    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
    +0.29
    1.1%
    1343
    +0.08
    0.3%
    1967
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2046
    +0.29
    0.04
    225
    +0.08
    0.03
    1739
    +0.07
    0.03
    Negative Logits
    <bos>
    -2.52
    <?
    -0.79
    ⓧ
    -0.74
     shuddered
    -0.67
     endeavored
    -0.67
     leaped
    -0.66
     disbur
    -0.65
     mustered
    -0.64
    ándor
    -0.61
     shivered
    -0.60
    POSITIVE LOGITS
     maroc
    0.95
     nomine
    0.91
     Politica
    0.86
     ananas
    0.85
     pép
    0.85
     banane
    0.84
     marte
    0.84
     ados
    0.82
     prostitu
    0.81
     vinci
    0.80
    Activations Density 0.079%

    No Known Activations