Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 309
    Prev
    Next
    INDEX
    Explanations

    mentions of sweating or sweat-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to clothing, particularly sweatshirts and shorts

    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
    ational
    -0.65
    ential
    -0.64
    gor
    -0.63
     Pegasus
    -0.62
    emon
    -0.61
     Axis
    -0.61
     Chimera
    -0.61
    inent
    -0.60
    ilion
    -0.60
     operator
    -0.59
    POSITIVE LOGITS
     sweats
    3.24
     sweat
    2.15
     jeans
    1.91
     shorts
    1.81
     Swe
    1.76
     sweater
    1.54
     sneakers
    1.38
     denim
    1.29
     swe
    1.23
    Swe
    1.20
    Activations Density 0.023%

    No Known Activations