© 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. 7035
    Prev
    Next
    INDEX
    Explanations

    words related to political decisions and actions

    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
    604
    +0.11
    0.3%
    1929
    +0.08
    0.2%
    1252
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.11
    0.07
    1531
    +0.08
    0.04
    1929
    +0.08
    0.04
    Negative Logits
     Cleanser
    -0.50
    <bos>
    -0.48
    internalType
    -0.46
    èdia
    -0.45
     foramen
    -0.45
    cheidet
    -0.44
     glandular
    -0.41
    xodo
    -0.39
    хіво
    -0.39
     conni
    -0.38
    POSITIVE LOGITS
     År
    0.71
     Muhamma
    0.63
     Valentín
    0.63
     Mejía
    0.60
     protesters
    0.60
     Tangerang
    0.58
     altrett
    0.57
     élégante
    0.57
     Joaqu
    0.57
     Michoacán
    0.57
    Activations Density 0.535%

    No Known Activations