© 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. 8-RES-JB
    11. 6443
    Prev
    Next
    INDEX
    Explanations

    medical terms or words related to medical procedures

    oai_token-act-pair · gpt-3.5-turbo

    words related to specialized medical or scientific terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Nev
    -0.73
    ãĤ±
    -0.71
    IRD
    -0.66
     Nev
    -0.66
    fair
    -0.65
     Seas
    -0.64
    Money
    -0.63
     Polk
    -0.63
     Craft
    -0.63
     Child
    -0.62
    POSITIVE LOGITS
    ttes
    0.80
    ktop
    0.78
     herself
    0.76
    eers
    0.75
    lease
    0.73
    gered
    0.71
    gery
    0.69
    acular
    0.69
    vous
    0.67
     themselves
    0.67
    Activations Density 0.346%

    No Known Activations