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. 13564
    Prev
    Next
    INDEX
    Explanations

    information related to statistical analysis and predictions in sports, particularly basketball and football

    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
    764
    +0.11
    0.3%
    1253
    +0.09
    0.3%
    1842
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.11
    0.04
    736
    +0.09
    0.07
    392
    +0.09
    0.03
    Negative Logits
     ftu
    -1.41
     §.
    -1.31
     effe
    -1.29
     aen
    -1.26
     fup
    -1.26
     paff
    -1.25
     mef
    -1.24
     magis
    -1.23
     meis
    -1.23
     ftre
    -1.22
    POSITIVE LOGITS
     superstar
    0.56
     dominating
    0.56
     himself
    0.55
     dominance
    0.54
     dominant
    0.53
     reigning
    0.52
     unparalleled
    0.52
     arguably
    0.50
     phenomenal
    0.50
     brilliant
    0.50
    Activations Density 0.683%

    No Known Activations