© 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. 4794
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptors related to emotional or social critique

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1363
    +0.12
    0.4%
    1343
    +0.11
    0.4%
    1535
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.12
    0.08
    615
    +0.11
    0.05
    820
    +0.11
    0.05
    Negative Logits
    <bos>
    -2.14
     vainly
    -1.13
     impelled
    -0.98
     endeavouring
    -0.97
     wilfully
    -0.93
     apprehen
    -0.90
     triumphantly
    -0.87
     roused
    -0.85
    
    -0.85
     innocently
    -0.84
    POSITIVE LOGITS
    eronau
    1.58
    dirond
    1.44
    capulco
    1.43
     sappi
    1.41
     dispen
    1.40
     pernic
    1.39
     incess
    1.39
     tass
    1.38
     bloss
    1.38
     tramont
    1.37
    Activations Density 0.324%

    No Known Activations