© 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. 1481
    Prev
    Next
    INDEX
    Explanations

    indicators used for separating parts in a document or a program

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks or separators

    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
    ecided
    -0.73
    milo
    -0.72
     torped
    -0.69
    schild
    -0.68
     disadvant
    -0.66
    jen
    -0.65
    obbies
    -0.65
    eryl
    -0.64
    jri
    -0.64
    undai
    -0.64
    POSITIVE LOGITS
     ][
    0.78
     Spectrum
    0.75
     Entered
    0.74
     SHARES
    0.73
     Provided
    0.73
     Registered
    0.70
     Franchise
    0.70
     Retro
    0.69
     Explicit
    0.69
    lement
    0.68
    Activations Density 0.018%

    No Known Activations