© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 22263
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms related to studies and research

    oai_token-act-pair · gpt-3.5-turbo

    references to health-related studies and outcomes involving specific demographics

    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
    INESS
    -0.81
    conom
    -0.79
    HCR
    -0.75
     Ideas
    -0.73
    THING
    -0.73
    ãĥķãĤ©
    -0.72
    phabet
    -0.72
    tainment
    -0.71
    imity
    -0.71
    inventoryQuantity
    -0.70
    POSITIVE LOGITS
     patients
    1.46
     elderly
    1.36
     obese
    1.35
     mice
    1.33
     adolescents
    1.31
     diabetic
    1.28
     rats
    1.27
     smokers
    1.24
     subjects
    1.20
     hypert
    1.20
    Activations Density 0.220%

    No Known Activations