© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 16872
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lesson" or "lessons" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to lessons learned from experiences or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    conn
    -0.66
    rosso
    -0.66
    bably
    -0.65
    ecided
    -0.64
    ipher
    -0.64
     flush
    -0.63
    brids
    -0.63
    endars
    -0.62
     contiguous
    -0.60
    idays
    -0.60
    POSITIVE LOGITS
     Learned
    1.20
     lessons
    1.01
    Lear
    1.00
     Teach
    0.96
     lesson
    0.95
     learned
    0.91
    ĸļ
    0.90
     learnt
    0.88
    learn
    0.85
     taught
    0.85
    Activations Density 0.038%

    No Known Activations