© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 4778
    Prev
    Next
    INDEX
    Explanations

    phrases related to competitive sports, especially focusing on individual players or teams

    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
    270
    +0.10
    0.3%
    674
    +0.08
    0.2%
    979
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.10
    0.06
    233
    +0.08
    0.04
    979
    +0.07
    0.05
    Negative Logits
     „,
    -1.67
     aen
    -1.55
     fuf
    -1.44
     mef
    -1.40
     fte
    -1.39
     fta
    -1.37
     fup
    -1.36
     ftu
    -1.35
     desir
    -1.31
     accla
    -1.31
    POSITIVE LOGITS
     ever
    0.91
    之一
    0.77
     imaginable
    0.70
     available
    0.69
     among
    0.68
     anywhere
    0.66
     EVER
    0.63
     anyone
    0.63
     alive
    0.61
     possible
    0.61
    Activations Density 0.199%

    No Known Activations