© 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. 3-RES-JB
    11. 1897
    Prev
    Next
    INDEX
    Explanations

    the word "body" occurring in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "body."

    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
     Bundy
    -0.73
    heny
    -0.70
     Cosponsors
    -0.69
     breeding
    -0.67
     FEC
    -0.66
     PBS
    -0.62
     Shutterstock
    -0.62
     Dickens
    -0.60
     liability
    -0.59
    hips
    -0.58
    POSITIVE LOGITS
    body
    1.10
    guards
    1.01
    hood
    0.89
    halla
    0.88
    bane
    0.87
    Else
    0.86
     else
    0.85
    else
    0.83
    bags
    0.83
    guard
    0.82
    Activations Density 0.010%

    No Known Activations