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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3079
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events and actions related to a government

    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
    51
    +0.17
    0.5%
    304
    +0.14
    0.5%
    1380
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.17
    0.04
    749
    +0.14
    0.03
    16
    +0.12
    0.04
    Negative Logits
    Casi
    -1.03
    Bajo
    -0.90
    Cuatro
    -0.88
    tarjetas
    -0.86
    Desta
    -0.86
    Recomend
    -0.86
    livro
    -0.86
    Embal
    -0.85
    Precis
    -0.85
    painel
    -0.84
    POSITIVE LOGITS
     „,
    2.73
     mef
    2.72
     wien
    2.69
     dises
    2.67
     seiz
    2.58
     nutr
    2.53
     exem
    2.50
     stockholm
    2.49
     effe
    2.48
     blos
    2.46
    Activations Density 0.173%

    No Known Activations