© 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. 7339
    Prev
    Next
    INDEX
    Explanations

    phrases related to invitations or events, specifically related to political or official gatherings

    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
    906
    +0.15
    0.5%
    674
    +0.11
    0.3%
    1741
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1291
    +0.15
    0.06
    1215
    +0.11
    0.04
    1288
    +0.11
    0.06
    Negative Logits
    cocina
    -0.52
     Paleozoic
    -0.49
    tetrahydro
    -0.47
    приєм
    -0.47
    devším
    -0.46
    Jeez
    -0.45
     이미
    -0.45
     acre
    -0.45
    творення
    -0.45
    Fatalf
    -0.44
    POSITIVE LOGITS
     dispen
    1.35
     kram
    1.33
     inder
    1.27
     lele
    1.25
     glan
    1.25
     profi
    1.22
     embra
    1.21
     dises
    1.21
     socie
    1.19
     hek
    1.19
    Activations Density 0.402%

    No Known Activations