Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 19327
    Prev
    Next
    INDEX
    Explanations

    medical procedures related to surgery

    oai_token-act-pair · gpt-3.5-turbo

    terms related to surgical procedures and medical conditions affecting the body

    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
    externalActionCode
    -0.84
    isSpecialOrderable
    -0.82
    soType
    -0.80
    izens
    -0.79
    bitious
    -0.78
    Maps
    -0.77
     newsp
    -0.71
     Pik
    -0.70
    Republic
    -0.68
     Saur
    -0.68
    POSITIVE LOGITS
     surgery
    1.14
     anesthesia
    1.13
     steril
    1.13
     surgeries
    1.12
     amput
    1.11
     Surgery
    1.10
     procedure
    1.09
     surg
    1.08
    ectomy
    1.03
    ysis
    1.02
    Activations Density 0.367%

    No Known Activations