© 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. 0-RES-JB
    11. 11402
    Prev
    Next
    INDEX
    Explanations

    words related to clothing, particularly t-shirts

    oai_token-act-pair · gpt-3.5-turbo

    words related to clothing items, specifically shirts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     composite
    -0.65
     counting
    -0.64
     stabbing
    -0.64
     saves
    -0.61
     Points
    -0.59
     sentencing
    -0.58
     processing
    -0.58
     killer
    -0.58
    greSQL
    -0.57
     optional
    -0.57
    POSITIVE LOGITS
    irt
    4.63
    irts
    2.55
    IRT
    2.29
    irted
    1.72
    irting
    1.56
    irty
    1.37
    irc
    1.23
    ird
    1.12
    irl
    1.07
    irst
    1.05
    Activations Density 0.015%

    No Known Activations