© 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. 10-RES-JB
    11. 12764
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    the medical terminology related to bodily functions and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.93
    ĸļ
    -0.90
    ington
    -0.79
    ipeg
    -0.75
    INGTON
    -0.74
    ãĥĦ
    -0.73
    ĵĺ
    -0.72
    sylvania
    -0.72
    ilater
    -0.71
    icum
    -0.70
    POSITIVE LOGITS
    mma
    1.29
    tto
    1.19
    ttes
    1.02
    tt
    0.98
    zza
    0.88
    vich
    0.86
    tti
    0.83
    tta
    0.83
    llan
    0.81
    tsky
    0.79
    Activations Density 0.057%

    No Known Activations