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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3875
    Prev
    Next
    INDEX
    Explanations

    references to a sports club in official statements and announcements

    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
    544
    +0.16
    0.7%
    1757
    +0.13
    0.5%
    1937
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    544
    +0.16
    0.04
    1416
    +0.13
    0.03
    938
    +0.12
    0.03
    Negative Logits
     nece
    -1.06
     effe
    -1.06
     fuf
    -1.02
     desir
    -1.00
     inev
    -1.00
     melissa
    -0.99
     macrop
    -0.99
     conspic
    -0.98
     purcha
    -0.98
     fte
    -0.97
    POSITIVE LOGITS
     club
    1.67
     Club
    1.56
    club
    1.56
     clubs
    1.54
    Club
    1.49
     Clubs
    1.40
     CLUB
    1.35
    clubs
    1.29
    CLUB
    1.28
    Clubs
    1.21
    Activations Density 0.083%

    No Known Activations