© 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. 1-RES-JB
    11. 3407
    Prev
    Next
    INDEX
    Explanations

    mentions of body parts or clothing-related phrases, especially related to neckwear

    oai_token-act-pair · gpt-3.5-turbo

    references to "collar," particularly in the context of types of collared clothing

    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
    endi
    -0.68
     NCT
    -0.67
     Blessed
    -0.66
    aren
    -0.64
    mitt
    -0.62
    ë
    -0.62
    efficient
    -0.61
     Anti
    -0.60
    conservancy
    -0.60
     Laksh
    -0.60
    POSITIVE LOGITS
    collar
    1.35
    bone
    1.31
     collar
    1.30
    bones
    1.28
    cloth
    0.79
    tie
    0.79
    ibrary
    0.78
     knit
    0.78
    neck
    0.78
     cuff
    0.76
    Activations Density 0.007%

    No Known Activations