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. 10143
    Prev
    Next
    INDEX
    Explanations

    information related to the celebration of Christmas, particularly focusing on aspects like traditions, holiday spirit, and gathering with family and friends

    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
    +0.11
    0.3%
    766
    +0.09
    0.3%
    330
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.11
    0.02
    1369
    +0.09
    0.02
    48
    +0.08
    0.03
    Negative Logits
     Præ
    -0.85
     §.
    -0.81
     „,
    -0.79
     Ibidem
    -0.78
     fatis
    -0.77
     cytoplas
    -0.74
     overla
    -0.74
     tille
    -0.73
     naer
    -0.71
     Græ
    -0.71
    POSITIVE LOGITS
     festive
    0.89
     Christmas
    0.80
     holiday
    0.79
    Christmas
    0.71
     Thanksgiving
    0.71
     festivities
    0.71
     decorations
    0.70
     christmas
    0.69
    🎄
    0.65
    holiday
    0.63
    Activations Density 0.479%

    No Known Activations