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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 784
    Prev
    Next
    INDEX
    Explanations

    key phrases that challenge or define truths in a political context

    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
    +0.18
    0.6%
    381
    +0.10
    0.3%
    198
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1419
    +0.18
    0.04
    1426
    +0.10
    0.04
    1757
    +0.10
    0.04
    Negative Logits
    <bos>
    -1.71
    Hahahahaha
    -1.03
    Hahah
    -0.99
    Cringe
    -0.96
    Fuckin
    -0.93
     milf
    -0.90
    /***
    
    -0.90
    Derp
    -0.85
    Ehh
    -0.84
     asf
    -0.83
    POSITIVE LOGITS
     bandung
    1.19
     Jambi
    1.17
     Karang
    1.15
     Minang
    1.10
     jawa
    1.08
     jaya
    1.03
     signora
    1.01
     papà
    0.97
     Palembang
    0.95
    öyle
    0.95
    Activations Density 0.484%

    No Known Activations