© 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. 0-RES-JB
    11. 8331
    Prev
    Next
    INDEX
    Explanations

    mentions of weeks of gestation and medical procedures related to pregnancy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gestation and pregnancy stages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eous
    -0.81
    eful
    -0.75
    crop
    -0.74
    imates
    -0.71
    vale
    -0.70
    erest
    -0.69
    airs
    -0.68
    inar
    -0.66
    cam
    -0.65
    ault
    -0.65
    POSITIVE LOGITS
     gestation
    1.30
     gest
    0.89
     Giov
    0.74
    alg
    0.67
     Birth
    0.65
     regul
    0.65
     Kad
    0.64
     Associ
    0.64
     preced
    0.64
     corrid
    0.63
    Activations Density 0.001%

    No Known Activations