© 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. 1854
    Prev
    Next
    INDEX
    Explanations

    references to a specific basketball coach or player, specifically focusing on their role and abilities within their team

    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
    1023
    +0.16
    0.7%
    900
    +0.14
    0.6%
    410
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1778
    +0.16
    0.04
    900
    +0.14
    0.04
    1363
    +0.13
    0.04
    Negative Logits
     précé
    -0.46
     suiv
    -0.45
     Madera
    -0.44
     Priya
    -0.44
     décid
    -0.43
     préc
    -0.42
     montrant
    -0.42
    Déf
    -0.41
    anueva
    -0.41
    strokeWidth
    -0.41
    POSITIVE LOGITS
     Ant
    1.18
    Ant
    1.10
     ant
    1.10
     ANT
    0.98
    ant
    0.98
    ANT
    0.93
     ants
    0.90
     Ants
    0.89
    antd
    0.77
    ants
    0.75
    Activations Density 0.253%

    No Known Activations