© 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. 7125
    Prev
    Next
    INDEX
    Explanations

    mentions of formal attire, particularly gowns

    oai_token-act-pair · gpt-3.5-turbo

    references to fashion, particularly gowns, and notable individuals associated with them

    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
    onom
    -0.79
     Mariners
    -0.69
    ãĥ
    -0.69
    fig
    -0.67
    ercise
    -0.65
    cium
    -0.63
     Wand
    -0.63
    ãĤ¿
    -0.63
    brain
    -0.63
     Brewers
    -0.62
    POSITIVE LOGITS
     cu
    0.83
    raq
    0.80
    rees
    0.80
    Reviewer
    0.79
    Thumbnail
    0.76
     gown
    0.75
    rices
    0.74
    rity
    0.73
     robes
    0.73
    roo
    0.72
    Activations Density 0.035%

    No Known Activations