© 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. 7-RES-JB
    11. 22895
    Prev
    Next
    INDEX
    Explanations

    phrases related to clothing items and styles

    oai_token-act-pair · gpt-3.5-turbo

    references to specific clothing and fashion items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     downstream
    -0.77
    onential
    -0.75
    rencies
    -0.74
    terness
    -0.72
     Nuclear
    -0.72
    ithmetic
    -0.70
    ETHOD
    -0.70
    Torrent
    -0.70
     Kumar
    -0.69
    uclear
    -0.68
    POSITIVE LOGITS
     worn
    1.52
     wardrobe
    1.26
     scarf
    1.26
     waist
    1.25
     adorned
    1.23
     trousers
    1.22
     sleeves
    1.21
     hairst
    1.21
     underwear
    1.18
     wore
    1.18
    Activations Density 0.555%

    No Known Activations