© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1995
    Prev
    Next
    INDEX
    Explanations

    relevant keywords and phrases related to news articles or editorials, potentially focusing on political topics and criticism of media and organizations

    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
    757
    +0.10
    0.3%
    1896
    +0.07
    0.2%
    897
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    757
    +0.10
    0.05
    173
    +0.07
    0.03
    1328
    +0.07
    0.03
    Negative Logits
     adjour
    -0.57
     précédemment
    -0.55
     viendra
    -0.54
     maneu
    -0.53
     renfer
    -0.53
     forfait
    -0.52
     Pamphlet
    -0.51
     malheureusement
    -0.51
     infallib
    -0.51
     raconte
    -0.50
    POSITIVE LOGITS
     solidar
    0.64
     Michoacán
    0.60
     evade
    0.57
     ecuador
    0.56
     detection
    0.55
     Mejía
    0.54
     Bahía
    0.53
     plak
    0.53
     Jerusal
    0.53
     psychiat
    0.52
    Activations Density 0.218%

    No Known Activations