© 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. 11-RES-JB
    11. 2512
    Prev
    Next
    INDEX
    Explanations

    items of clothing and accessories

    oai_token-act-pair · gpt-3.5-turbo

    recommendations related to clothing and safety gear

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akespeare
    -0.82
    terness
    -0.82
    Mill
    -0.79
    acre
    -0.76
    Plot
    -0.76
    ynchronous
    -0.74
     Rowling
    -0.73
    Lu
    -0.72
    æĺ
    -0.69
    luence
    -0.67
    POSITIVE LOGITS
     gloves
    1.91
     helmets
    1.90
     goggles
    1.88
     helmet
    1.85
     straps
    1.60
     sunglasses
    1.60
     Gloves
    1.56
     Helmet
    1.52
     socks
    1.51
     footwear
    1.49
    Activations Density 0.393%

    No Known Activations