Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 945
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the name "David Stock."

    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%
    184
    +0.21
    0.8%
    1343
    +0.20
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.24
    0.07
    184
    +0.21
    0.02
    119
    +0.20
    0.04
    Negative Logits
    <bos>
    -3.76
     Мексичка
    -0.89
     Italijani
    -0.88
    Panamoan
    -0.86
    Autoritní
    -0.83
    Vidite
    -0.83
     Савезне
    -0.80
     Administrativna
    -0.79
    Personendaten
    -0.78
    GEBURTSDATUM
    -0.78
    POSITIVE LOGITS
     milano
    1.58
     napoli
    1.57
     meis
    1.52
     stockholm
    1.46
     emphat
    1.46
     madonna
    1.43
     lele
    1.41
     inev
    1.40
     wien
    1.40
     bordeaux
    1.38
    Activations Density 0.175%

    No Known Activations