© 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. 3-RES-JB
    11. 24447
    Prev
    Next
    INDEX
    Explanations

    URL links

    oai_token-act-pair · gpt-3.5-turbo

    URLs or web links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Frie
    -0.82
    ĪĴ
    -0.67
     Sut
    -0.66
     sanity
    -0.65
     Pyramid
    -0.64
    ulia
    -0.64
     Mush
    -0.63
    senal
    -0.62
     Horizons
    -0.61
     Falls
    -0.61
    POSITIVE LOGITS
    ffee
    1.03
    verage
    0.95
    xon
    0.89
    fman
    0.86
    ff
    0.84
    ertodd
    0.84
    Desk
    0.83
    oldown
    0.83
    ingen
    0.80
    ipel
    0.80
    Activations Density 0.008%

    No Known Activations