Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18091
    Prev
    Next
    INDEX
    Explanations

    words related to bathroom facilities and transgender rights

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bathrooms and restroom facilities in the context of transgender rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovsky
    -0.70
    epad
    -0.67
     subsequ
    -0.66
    arily
    -0.65
    alam
    -0.65
    pend
    -0.64
    eq
    -0.63
     prem
    -0.62
    istically
    -0.61
    ombie
    -0.60
    POSITIVE LOGITS
     stalls
    1.04
     toilets
    0.88
     restroom
    0.88
    itory
    0.83
     bathroom
    0.83
     bathrooms
    0.80
     restrooms
    0.77
    robe
    0.76
     stall
    0.76
     hygiene
    0.72
    Activations Density 0.022%

    No Known Activations