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. 13954
    Prev
    Next
    INDEX
    Explanations

    references to football plays, specifically involving tackling

    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
    1145
    +0.20
    0.8%
    795
    +0.16
    0.6%
    896
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1145
    +0.20
    0.03
    795
    +0.16
    0.02
    438
    +0.12
    0.02
    Negative Logits
     mélang
    -0.56
     jouant
    -0.56
     amélior
    -0.55
     exé
    -0.55
     élar
    -0.55
     appré
    -0.54
     gardent
    -0.54
     écou
    -0.53
     roth
    -0.53
     appuy
    -0.53
    POSITIVE LOGITS
     tackle
    1.22
     tackles
    1.13
     tackled
    1.11
     tackling
    1.05
     Tackle
    0.93
    Tack
    0.88
    tack
    0.81
     Tack
    0.78
     hashlib
    0.66
     tack
    0.64
    Activations Density 0.073%

    No Known Activations