© 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. 8-RES-JB
    11. 2737
    Prev
    Next
    INDEX
    Explanations

    clothing items and accessories

    oai_token-act-pair · gpt-3.5-turbo

    clothing and fashion accessories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otten
    -0.74
    Refer
    -0.73
    enthal
    -0.72
    Interest
    -0.71
    nuclear
    -0.69
    issions
    -0.69
    KNOWN
    -0.68
    Dev
    -0.68
    DEV
    -0.67
     Site
    -0.66
    POSITIVE LOGITS
     worn
    1.30
     adorned
    1.23
     draped
    1.10
    cloth
    1.06
     wearer
    1.04
     fashioned
    1.01
     clad
    1.00
     sleeves
    1.00
     trousers
    1.00
     jacket
    0.99
    Activations Density 0.152%

    No Known Activations