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. 6829
    Prev
    Next
    INDEX
    Explanations

    references to Israeli political figures, particularly Netanyahu

    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
    1589
    +0.13
    0.5%
    50
    +0.11
    0.4%
    1984
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.13
    0.05
    1609
    +0.11
    0.04
    1987
    +0.11
    0.04
    Negative Logits
    <bos>
    -1.52
     universale
    -0.60
     exé
    -0.58
    MOQ
    -0.58
    VStack
    -0.58
    HStack
    -0.58
    writeField
    -0.56
    estimable
    -0.55
    DockStyle
    -0.55
     nakalista
    -0.54
    POSITIVE LOGITS
    anyahu
    0.79
     Netanyahu
    0.69
     Oberlin
    0.67
     brooklyn
    0.67
     eiffel
    0.65
     Mónica
    0.64
     Trudeau
    0.64
     arroyo
    0.63
     cartier
    0.62
     caribbean
    0.60
    Activations Density 0.106%

    No Known Activations