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. 15257
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and fundraising efforts

    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
    1515
    +0.15
    0.5%
    1491
    +0.13
    0.5%
    1806
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1515
    +0.15
    0.04
    1806
    +0.13
    0.04
    1565
    +0.13
    0.03
    Negative Logits
     décro
    -0.60
     Sne
    -0.52
     carrefour
    -0.51
     panik
    -0.50
     ralenti
    -0.48
     papillon
    -0.48
     Avez
    -0.48
     récla
    -0.48
     renfer
    -0.46
     moulin
    -0.46
    POSITIVE LOGITS
     raise
    1.29
     raised
    1.23
     raising
    1.19
    raise
    1.18
     raises
    1.17
     Raise
    1.16
    raised
    1.16
    Raising
    1.05
    Raise
    1.03
    raising
    1.01
    Activations Density 0.099%

    No Known Activations