© 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. 5106
    Prev
    Next
    INDEX
    Explanations

    phrases expressing varying degrees of acceptance and approval

    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
    +0.15
    0.5%
    478
    +0.14
    0.5%
    897
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    897
    +0.15
    0.04
    623
    +0.14
    0.04
    1095
    +0.13
    0.03
    Negative Logits
    <bos>
    -0.92
     apprehen
    -0.90
     Shakspeare
    -0.89
     forbear
    -0.88
     vainly
    -0.88
     impelled
    -0.85
     unspeak
    -0.84
     endeavouring
    -0.82
    
    -0.82
     disagre
    -0.82
    POSITIVE LOGITS
    quarelle
    0.89
     giu
    0.76
     bienven
    0.76
    ciclop
    0.74
     frambo
    0.74
    dialement
    0.71
     cottura
    0.71
    WriteTagHelper
    0.69
     secco
    0.69
    eronau
    0.69
    Activations Density 0.195%

    No Known Activations