© 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. 7-RES-JB
    11. 3869
    Prev
    Next
    INDEX
    Explanations

    references to various items of clothing or accessories being worn by someone

    oai_token-act-pair · gpt-3.5-turbo

    references to clothing and apparel

    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
    llor
    -0.87
    emetery
    -0.85
    ezvous
    -0.79
    raq
    -0.77
    ancock
    -0.76
    terness
    -0.75
     Revenue
    -0.75
    orage
    -0.74
    ruciating
    -0.74
    ependence
    -0.72
    POSITIVE LOGITS
     clothes
    1.10
     shirt
    1.05
     gloves
    1.04
     sleeves
    1.04
     underwear
    1.04
     goggles
    1.02
     jacket
    1.01
     robes
    0.99
     sleeve
    0.99
     socks
    0.98
    Activations Density 0.114%

    No Known Activations