Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15817
    Prev
    Next
    INDEX
    Explanations

    phrases expressing appreciation or acknowledgments

    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
    62
    +0.09
    0.2%
    581
    +0.08
    0.2%
    648
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.09
    0.04
    267
    +0.08
    0.04
    2045
    +0.07
    0.04
    Negative Logits
     Juf
    -1.32
     volunte
    -1.29
     „,
    -1.26
     fuf
    -1.24
     unlaw
    -1.24
     accla
    -1.24
     reluct
    -1.21
     Augu
    -1.21
     strick
    -1.20
     §.
    -1.19
    POSITIVE LOGITS
     is
    0.84
    คือ
    0.67
    的是
    0.67
    は
    0.60
     involves
    0.59
     adalah
    0.58
     are
    0.57
     है
    0.57
    은
    0.56
     הוא
    0.55
    Activations Density 0.154%

    No Known Activations