© 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. 6-RES-JB
    11. 11571
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical procedures being performed

    oai_token-act-pair · gpt-3.5-turbo

    references to surgical procedures and medical interventions

    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
     bragging
    -0.78
     Strongh
    -0.76
    gemony
    -0.72
     Electoral
    -0.71
     widgets
    -0.71
    campaign
    -0.71
    alist
    -0.70
     revolt
    -0.70
     bookmark
    -0.70
    inous
    -0.69
    POSITIVE LOGITS
     Canaver
    1.11
     anesthesia
    1.10
     Doctors
    1.09
     treatments
    1.09
    treatment
    1.08
     doctors
    1.08
     patients
    1.04
     treating
    1.03
     surgeries
    1.03
     cure
    1.03
    Activations Density 0.518%

    No Known Activations