© 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. 4934
    Prev
    Next
    INDEX
    Explanations

    occurrences of the pronoun "I" and related phrases indicating personal perspective

    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
    +0.36
    1.9%
    381
    +0.18
    1.0%
    1741
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    805
    +0.36
    0.13
    1919
    +0.18
    0.13
    381
    +0.12
    0.07
    Negative Logits
    <bos>
    -2.15
     guma
    -0.78
     MÁ
    -0.74
    ///**
    -0.66
     EoL
    -0.66
    /***
    -0.65
    ⓧ
    -0.64
    脚注の使い方
    -0.63
     panahon
    -0.62
     springfox
    -0.61
    POSITIVE LOGITS
     reluct
    1.40
     shenan
    1.29
     accla
    1.29
     maneu
    1.23
     apprehen
    1.19
     practition
    1.19
     impra
    1.18
     disagre
    1.15
     disgra
    1.15
     unspeak
    1.12
    Activations Density 0.312%

    No Known Activations