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. 551
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics and healthcare legislation, specifically focusing on the Affordable Care Act

    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
    1842
    +0.12
    0.3%
    1870
    +0.10
    0.3%
    316
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1618
    +0.12
    0.02
    1105
    +0.10
    0.03
    914
    +0.09
    0.02
    Negative Logits
     useRouter
    -0.56
     mourut
    -0.55
     Février
    -0.55
     automne
    -0.54
     biex
    -0.54
     Décembre
    -0.54
     mignon
    -0.51
    potensi
    -0.51
     useParams
    -0.50
     devint
    -0.50
    POSITIVE LOGITS
     saar
    0.94
     kasa
    0.88
     kaos
    0.88
     teras
    0.80
     kark
    0.78
     Jä
    0.78
     kram
    0.78
     territo
    0.76
     tyn
    0.75
     Erfurt
    0.74
    Activations Density 0.117%

    No Known Activations