© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12577
    Prev
    Next
    INDEX
    Explanations

    verbs related to improvement and the concept of making things better

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    390
    +0.12
    0.4%
    544
    +0.11
    0.4%
    196
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1398
    +0.12
    0.02
    1142
    +0.11
    0.03
    390
    +0.10
    0.03
    Negative Logits
     suscep
    -0.95
     indestru
    -0.94
     guarante
    -0.90
     reluct
    -0.88
     unden
    -0.85
     volunte
    -0.84
     affor
    -0.84
     fuf
    -0.82
     disreg
    -0.82
     erad
    -0.81
    POSITIVE LOGITS
     improve
    0.92
     improvement
    0.92
     improvements
    0.90
     Improvement
    0.88
    improve
    0.88
     Improve
    0.86
    improvement
    0.84
     improving
    0.83
     improved
    0.82
     improves
    0.80
    Activations Density 0.088%

    No Known Activations