© 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. 2-RES-JB
    11. 17216
    Prev
    Next
    INDEX
    Explanations

    references to controversial bathroom bills and related discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to bathroom-related issues and policies, particularly those affecting transgender rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    guided
    -0.75
    eq
    -0.70
    epad
    -0.68
    held
    -0.64
     subsequ
    -0.64
    pend
    -0.62
    onel
    -0.62
    udic
    -0.61
    */(
    -0.61
    ombie
    -0.60
    POSITIVE LOGITS
     stalls
    1.14
     restroom
    0.98
     toilets
    0.97
     bathroom
    0.91
     bathrooms
    0.90
     restrooms
    0.90
    ãĤ£
    0.80
     stall
    0.80
     hygiene
    0.77
     cleaners
    0.75
    Activations Density 0.011%

    No Known Activations