© 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. 1-RES-JB
    11. 23043
    Prev
    Next
    INDEX
    Explanations

    medical terms or substances used in clinical trials

    oai_token-act-pair · gpt-3.5-turbo

    terms related to placebo effects and placebo-controlled studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eways
    -0.75
    hani
    -0.72
     IPM
    -0.70
    dar
    -0.70
    Greg
    -0.69
    Fran
    -0.69
    Golden
    -0.68
    laws
    -0.68
    EMA
    -0.67
    San
    -0.67
    POSITIVE LOGITS
     placebo
    1.36
    veyard
    0.90
     analges
    0.78
     conclud
    0.76
     acupuncture
    0.73
     sham
    0.73
    nesday
    0.71
    icter
    0.71
     augment
    0.70
     Pengu
    0.69
    Activations Density 0.010%

    No Known Activations