© 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. 9-RES-JB
    11. 1997
    Prev
    Next
    INDEX
    Explanations

    adjectives describing physical appearance or design

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to visual appearance or aesthetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stem
    -0.75
    learning
    -0.68
     Tosh
    -0.65
    wealth
    -0.65
     EPS
    -0.65
    Market
    -0.62
    ciating
    -0.61
    foreseen
    -0.61
    onto
    -0.59
     Excel
    -0.59
    POSITIVE LOGITS
    ahead
    0.99
    behind
    0.77
    prints
    0.68
    ative
    0.67
    checks
    0.66
    ":"/
    0.64
    finder
    0.64
    print
    0.64
    gio
    0.63
    tty
    0.62
    Activations Density 0.058%

    No Known Activations