© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 4851
    Prev
    Next
    INDEX
    Explanations

    sections in a text that have been edited

    oai_token-act-pair · gpt-3.5-turbo

    sections or headings of structured content, particularly in academic or informational texts

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

    No Comments

    Negative Logits
    hement
    -0.81
     citiz
    -0.80
     ende
    -0.73
    userc
    -0.71
    umbers
    -0.69
     incarcer
    -0.69
    terday
    -0.68
     neighb
    -0.66
     naughty
    -0.66
     choking
    -0.65
    POSITIVE LOGITS
    References
    1.01
    Trivia
    0.93
    âĨij
    0.83
    Associated
    0.80
    Appearances
    0.80
    Gallery
    0.79
    ccording
    0.79
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.78
    >>>>>>>>
    0.76
    Production
    0.75
    Activations Density 0.082%

    No Known Activations