© 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. 13270
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "that" where the following words are qualitatively describing something

    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
    674
    +0.19
    0.7%
    161
    +0.19
    0.7%
    1350
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    161
    +0.19
    0.11
    1023
    +0.19
    0.09
    1350
    +0.14
    0.08
    Negative Logits
     lts
    -1.11
     lein
    -1.08
     aen
    -1.05
     affor
    -1.05
     Confu
    -1.04
     inappro
    -1.03
     unden
    -1.03
     Middles
    -1.03
     parch
    -1.02
     walter
    -1.01
    POSITIVE LOGITS
    <bos>
    0.97
     that
    0.85
     THAT
    0.79
    that
    0.77
    THAT
    0.70
     That
    0.69
    That
    0.65
     dat
    0.62
     que
    0.59
    Eso
    0.57
    Activations Density 0.342%

    No Known Activations