© 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. 10-RES-JB
    11. 20549
    Prev
    Next
    INDEX
    Explanations

    chemical names and medications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to substances and their chemical or medical properties

    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
     Purg
    -0.73
     Lands
    -0.71
     Smithsonian
    -0.69
     Photographer
    -0.69
     Panda
    -0.69
     Puppet
    -0.69
     Gunn
    -0.67
     Fork
    -0.67
     Pagan
    -0.67
     Revel
    -0.66
    POSITIVE LOGITS
    amide
    1.55
    idine
    1.46
    amine
    1.32
    anol
    1.31
    oxide
    1.24
    oxin
    1.23
    aldehyde
    1.23
    amphetamine
    1.21
    azine
    1.21
    iaz
    1.16
    Activations Density 0.109%

    No Known Activations