© 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. 12386
    Prev
    Next
    INDEX
    Explanations

    terms related to basketball defense, particularly focusing on critiques of player defense skills

    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
    31
    +0.12
    0.4%
    1828
    +0.12
    0.4%
    674
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1828
    +0.12
    0.10
    31
    +0.12
    0.08
    341
    +0.12
    0.08
    Negative Logits
     Pourtant
    -0.58
     Donc
    -0.54
     Leurs
    -0.53
    AndEndTag
    -0.52
    }[!
    -0.52
    jectures
    -0.52
     Même
    -0.50
    Beaucoup
    -0.50
    Plusieurs
    -0.49
    haustible
    -0.49
    POSITIVE LOGITS
     récomp
    0.90
     récon
    0.88
     dénon
    0.88
     nettoy
    0.82
     mémor
    0.80
     vété
    0.79
     chantier
    0.76
     mépris
    0.75
     délib
    0.74
     pavillon
    0.74
    Activations Density 0.325%

    No Known Activations