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. 15975
    Prev
    Next
    INDEX
    Explanations

    information related to the history and resurgence of certain typefaces/fonts

    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
    1121
    +0.07
    0.2%
    1181
    +0.07
    0.2%
    945
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1181
    +0.07
    0.05
    945
    +0.07
    0.04
    175
    +0.07
    0.05
    Negative Logits
    hésite
    -0.62
     siè
    -0.62
     surfact
    -0.62
    "}")
    -0.61
     glau
    -0.60
     venons
    -0.58
     itemList
    -0.57
     ejus
    -0.56
     Améli
    -0.56
     §.
    -0.56
    POSITIVE LOGITS
     popularity
    0.95
     success
    0.77
     Popularity
    0.70
     craze
    0.66
     successes
    0.65
     popular
    0.65
     successful
    0.58
     Success
    0.58
     succeed
    0.58
     fame
    0.57
    Activations Density 0.563%

    No Known Activations