© 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. 1457
    Prev
    Next
    INDEX
    Explanations

    the letters "sa" followed by specific combinations of characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sa" used prominently in various contexts

    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
    INGTON
    -0.78
    ãĥ¼ãĥĨãĤ£
    -0.70
    hips
    -0.68
    LIN
    -0.68
     Dragonbound
    -0.67
    itarian
    -0.65
    DragonMagazine
    -0.65
    enegger
    -0.63
    etheless
    -0.63
    ruary
    -0.62
    POSITIVE LOGITS
    pling
    1.26
    ven
    1.13
    plings
    1.10
    arin
    1.04
    uth
    1.03
    ucer
    1.00
    ppy
    0.99
    xon
    0.99
    uten
    0.98
    llan
    0.97
    Activations Density 0.011%

    No Known Activations