© 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. 10-RES-JB
    11. 13904
    Prev
    Next
    INDEX
    Explanations

    key lessons or insights mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to lessons learned or teachings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     occupancy
    -0.74
    omin
    -0.71
    trak
    -0.68
    umbers
    -0.64
    FP
    -0.64
    BLIC
    -0.62
    chairs
    -0.62
    hw
    -0.62
    endars
    -0.62
    ãĥ¢
    -0.61
    POSITIVE LOGITS
     Learned
    1.55
     learned
    1.50
     learnt
    1.42
     lesson
    1.24
     lessons
    1.23
    Lear
    1.12
    learn
    1.10
     taught
    1.03
     glean
    0.93
     Lessons
    0.89
    Activations Density 0.051%

    No Known Activations