© 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. 13468
    Prev
    Next
    INDEX
    Explanations

    phrases related to military drills and disciplinary actions

    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
    906
    +0.14
    0.4%
    1959
    +0.12
    0.4%
    1843
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1959
    +0.14
    0.09
    1009
    +0.12
    0.03
    2016
    +0.11
    0.06
    Negative Logits
    介入
    -0.54
    They
    -0.54
    It
    -0.52
     They
    -0.51
    抽出
    -0.51
     about
    -0.50
    全集
    -0.49
    孤立
    -0.49
     It
    -0.49
    留意
    -0.48
    POSITIVE LOGITS
     megane
    1.21
     swarovski
    1.19
     thermomix
    1.18
     sappi
    1.17
     broderie
    1.16
     tricot
    1.14
     paillettes
    1.13
     chèvre
    1.12
     cabrio
    1.07
     Angleterre
    1.05
    Activations Density 1.344%

    No Known Activations