© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 2238
    Prev
    Next
    INDEX
    Explanations

    terms related to political figures named "Ryan"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1757
    +0.15
    0.6%
    1101
    +0.14
    0.6%
    544
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1101
    +0.15
    0.02
    1757
    +0.14
    0.02
    544
    +0.13
    0.02
    Negative Logits
     shayari
    -0.54
     cushi
    -0.53
    chong
    -0.52
     shenan
    -0.48
    SPECTION
    -0.48
     uchiha
    -0.47
     userType
    -0.47
     Benzene
    -0.47
     superare
    -0.46
     perdere
    -0.45
    POSITIVE LOGITS
     Ryan
    1.48
    Ryan
    1.40
     ryan
    1.17
    ryan
    0.89
     Ry
    0.81
    Ry
    0.69
     ry
    0.67
     RY
    0.61
     Ryanair
    0.59
    RY
    0.57
    Activations Density 0.097%

    No Known Activations