© 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. 10-RES-JB
    11. 11489
    Prev
    Next
    INDEX
    Explanations

    medical conditions and related keywords

    oai_token-act-pair · gpt-3.5-turbo

    medical conditions and their treatment options

    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
     Mahjong
    -0.79
    soDeliveryDate
    -0.77
     srfAttach
    -0.67
     negotiators
    -0.67
     bargain
    -0.66
     Alphabet
    -0.66
     Catalog
    -0.65
     classy
    -0.65
     warehouses
    -0.65
     Logo
    -0.64
    POSITIVE LOGITS
     pneumonia
    1.32
    inflamm
    1.30
     asthma
    1.25
    cancer
    1.23
     Syndrome
    1.23
    clerosis
    1.23
    iasis
    1.20
    thritis
    1.19
     Symptoms
    1.19
     syndrome
    1.17
    Activations Density 0.191%

    No Known Activations