© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 6608
    Prev
    Next
    INDEX
    Explanations

    phrases related to caution and warning

    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
    1926
    +0.14
    0.4%
    341
    +0.13
    0.4%
    1839
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.14
    0.03
    1776
    +0.13
    0.02
    1926
    +0.12
    0.03
    Negative Logits
     disagre
    -0.66
     plong
    -0.62
     indestru
    -0.61
     trouvera
    -0.60
     renou
    -0.59
     Juf
    -0.57
     ineffec
    -0.57
     prétend
    -0.56
     impra
    -0.55
     clô
    -0.55
    POSITIVE LOGITS
     careful
    1.03
     carefully
    0.89
     Carefully
    0.79
    Careful
    0.78
     Careful
    0.77
     cautious
    0.76
    caref
    0.75
     caution
    0.72
     cuidado
    0.64
     precautions
    0.63
    Activations Density 0.106%

    No Known Activations