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. 3072
    Prev
    Next
    INDEX
    Explanations

    phrases related to weddings and events associated with weddings

    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
    1013
    +0.13
    0.4%
    314
    +0.09
    0.3%
    776
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.13
    0.04
    1244
    +0.09
    0.02
    1971
    +0.08
    0.02
    Negative Logits
     dovr
    -0.85
     simplif
    -0.85
     remplace
    -0.83
     soggior
    -0.81
     constate
    -0.80
     préc
    -0.79
     appunt
    -0.78
     brille
    -0.76
     carrefour
    -0.76
     récla
    -0.75
    POSITIVE LOGITS
     wedding
    1.26
    wedding
    1.09
     weddings
    1.08
     Wedding
    1.07
    Wedding
    0.99
     Weddings
    0.86
     bride
    0.84
     bridal
    0.81
     ceremony
    0.79
    eddings
    0.78
    Activations Density 0.296%

    No Known Activations