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. 13638
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes and plans for the future

    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
    663
    +0.11
    0.4%
    130
    +0.10
    0.3%
    755
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    663
    +0.11
    0.04
    911
    +0.10
    0.04
    130
    +0.09
    0.07
    Negative Logits
     perfon
    -1.08
     desir
    -1.08
     leaft
    -1.06
     fays
    -1.05
     reft
    -1.05
     feen
    -1.05
     laft
    -1.02
     secon
    -1.02
     fup
    -1.02
     ftre
    -1.00
    POSITIVE LOGITS
     maraming
    0.78
     pagkak
    0.72
     betweenstory
    0.67
     bagay
    0.63
     buhay
    0.63
     autorytatywna
    0.62
     bawat
    0.62
     intptr
    0.62
     sarili
    0.62
     Wikimédia
    0.60
    Activations Density 0.825%

    No Known Activations