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. 529
    Prev
    Next
    INDEX
    Explanations

    words related to holidays and festive seasons

    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
    1870
    +0.16
    0.6%
    1778
    +0.14
    0.5%
    1993
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1778
    +0.16
    0.02
    1092
    +0.14
    0.02
    1993
    +0.12
    0.02
    Negative Logits
    zdroj
    -0.52
    ellemző
    -0.52
    ingeki
    -0.51
    Glej
    -0.46
    geslacht
    -0.44
    TEntity
    -0.43
    Zitat
    -0.43
    rozum
    -0.42
     GenerationType
    -0.42
     dégust
    -0.42
    POSITIVE LOGITS
     holiday
    1.36
     holidays
    1.25
    holiday
    1.22
     Holiday
    1.19
    Holiday
    1.15
     Holidays
    1.09
    holidays
    1.04
     HOLIDAY
    1.03
     vacation
    0.98
    Holidays
    0.86
    Activations Density 0.071%

    No Known Activations