© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 11608
    Prev
    Next
    INDEX
    Explanations

    words related to headwear, specifically hats

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Hat" and variations thereof in the context of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.94
     UNIVERS
    -0.81
    theless
    -0.79
     glutamate
    -0.70
    DonaldTrump
    -0.65
    ournal
    -0.64
    sample
    -0.61
    successfully
    -0.61
    margin
    -0.60
    trl
    -0.60
    POSITIVE LOGITS
    chery
    1.10
     Hat
    1.03
    chet
    1.03
    Hat
    1.01
    dar
    0.89
    cher
    0.86
    red
    0.79
    gart
    0.77
    rack
    0.77
    ches
    0.76
    Activations Density 0.005%

    No Known Activations