© 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. 6-RES-JB
    11. 3580
    Prev
    Next
    INDEX
    Explanations

    physical symptoms and conditions related to swelling, itching, irritation, and inflammation

    oai_token-act-pair · gpt-3.5-turbo

    medical terms related to skin reactions and symptoms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rolet
    -0.82
    zees
    -0.69
    =-=-=-=-=-=-=-=-
    -0.68
    winner
    -0.67
     Tradable
    -0.66
     minister
    -0.66
     sender
    -0.64
    undai
    -0.64
    soDeliveryDate
    -0.63
    imental
    -0.63
    POSITIVE LOGITS
     swelling
    1.00
     symptoms
    0.94
     glands
    0.93
    ptoms
    0.93
     Symptoms
    0.93
     healed
    0.92
     pores
    0.92
     inflammation
    0.89
     lesions
    0.87
     muc
    0.85
    Activations Density 0.257%

    No Known Activations