© 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. 11-RES-JB
    11. 9424
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical procedures and conditions, such as patient care and treatment

    oai_token-act-pair · gpt-3.5-turbo

    references to medical procedures and physical anatomy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     weddings
    -0.72
     Nightmares
    -0.69
     kisses
    -0.68
     Challenges
    -0.68
     kittens
    -0.67
     orphans
    -0.67
    votes
    -0.66
     hikers
    -0.66
     rookies
    -0.66
     Solitaire
    -0.65
    POSITIVE LOGITS
     body
    0.83
     physical
    0.82
     material
    0.82
     organism
    0.80
     anatomy
    0.78
     underlying
    0.71
     physically
    0.69
     source
    0.69
     environment
    0.68
     information
    0.67
    Activations Density 0.659%

    No Known Activations