© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19856
    Prev
    Next
    INDEX
    Explanations

    mentions of clothing items, specifically shorts

    oai_token-act-pair · gpt-3.5-turbo

    references to shorts and specific types of clothing

    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
    henko
    -0.78
    velt
    -0.75
    ught
    -0.75
     Myster
    -0.74
    ucha
    -0.72
    steen
    -0.72
    tein
    -0.71
    cients
    -0.71
     Prin
    -0.71
    ocker
    -0.70
    POSITIVE LOGITS
     shorts
    2.17
     ranc
    1.64
     Rapt
    1.22
     rapt
    1.21
     Leigh
    1.16
     Louise
    1.11
     Hicks
    1.06
    icol
    1.03
     ranch
    0.94
     Soy
    0.92
    Activations Density 0.036%

    No Known Activations