© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3551
    Prev
    Next
    INDEX
    Explanations

    adverbs denoting extent or degree

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    1482
    +0.17
    0.6%
    994
    +0.12
    0.4%
    537
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1482
    +0.17
    0.06
    537
    +0.12
    0.04
    201
    +0.11
    0.03
    Negative Logits
     inconce
    -0.63
     inev
    -0.62
     orch
    -0.62
     accla
    -0.60
     suppos
    -0.60
     insensible
    -0.58
     Pyrene
    -0.58
     emphat
    -0.57
     disagre
    -0.57
     circums
    -0.56
    POSITIVE LOGITS
    even
    0.85
     even
    0.82
     EVEN
    0.75
    Even
    0.70
     Even
    0.69
    EVEN
    0.66
    Même
    0.62
    <bos>
    0.59
    cydow
    0.57
    SharedDtor
    0.56
    Activations Density 0.085%

    No Known Activations