© 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. 14585
    Prev
    Next
    INDEX
    Explanations

    references to breastfeeding

    oai_token-act-pair · gpt-3.5-turbo

    references to breast milk and breast-related health issues

    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
    alien
    -0.74
     Amend
    -0.73
    upon
    -0.73
     Bravo
    -0.70
    pmwiki
    -0.70
    eff
    -0.69
     Immunity
    -0.67
    umar
    -0.66
    MER
    -0.66
     Illegal
    -0.64
    POSITIVE LOGITS
     breast
    1.16
     breasts
    1.08
    bone
    1.07
    plate
    1.03
     nipple
    1.01
     nipples
    0.99
     milk
    0.89
     Breast
    0.88
    fed
    0.84
     implants
    0.84
    Activations Density 0.006%

    No Known Activations