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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4637
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events, particularly focusing on challenges and outcomes in competitions

    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
    +0.31
    1.2%
    604
    +0.13
    0.5%
    344
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.31
    0.07
    344
    +0.13
    0.06
    1135
    +0.11
    0.06
    Negative Logits
    <bos>
    -3.16
    Geplaatst
    -0.80
    Autoritní
    -0.78
    addCriterion
    -0.64
    GEBURTSDATUM
    -0.63
     kwiet
    -0.62
     насеља
    -0.59
     <<-
    -0.59
     _("
    -0.58
     '%'
    -0.57
    POSITIVE LOGITS
     Khart
    1.31
     panik
    1.17
     Muhamma
    1.14
     Palembang
    1.11
     Heeren
    1.09
     Czechos
    1.08
     Fulda
    1.08
     akut
    1.08
     Minang
    1.07
     kado
    1.07
    Activations Density 1.103%

    No Known Activations