© 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. 10-RES-JB
    11. 14119
    Prev
    Next
    INDEX
    Explanations

    medical-related terms and actions, such as seeking care, treatment, and consulting specialists

    oai_token-act-pair · gpt-3.5-turbo

    references to medical care and treatment processes

    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
     Winners
    -0.81
    yrights
    -0.81
    eny
    -0.74
     Democr
    -0.71
    Iss
    -0.71
     blat
    -0.67
    BW
    -0.66
    ween
    -0.65
     Skies
    -0.64
    estamp
    -0.63
    POSITIVE LOGITS
     therapy
    1.76
     counseling
    1.73
     therapists
    1.68
     therapies
    1.67
     counselling
    1.67
     medication
    1.61
     therapist
    1.59
     medications
    1.55
     medicine
    1.53
     outpatient
    1.52
    Activations Density 0.983%

    No Known Activations