© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1367
    Prev
    Next
    INDEX
    Explanations

    instances of sitting or positioning of individuals

    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
    50
    +0.24
    0.9%
    1013
    +0.11
    0.4%
    370
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.24
    0.05
    906
    +0.11
    0.00
    1479
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.21
     declare
    -0.57
     ratify
    -0.52
     denounce
    -0.52
    Globalization
    -0.51
     accrue
    -0.50
     supersede
    -0.50
    TargetException
    -0.50
     enshr
    -0.49
     Moh
    -0.49
    POSITIVE LOGITS
     wattpad
    1.10
     seating
    1.01
    capulco
    0.94
    dirond
    0.94
     Seating
    0.89
     seat
    0.89
     seats
    0.88
     hentai
    0.86
     genshin
    0.86
     luffy
    0.85
    Activations Density 0.175%

    No Known Activations