© 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. 4-RES-JB
    11. 10463
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "transgender" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to transgender individuals and issues related to their rights

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

    No Comments

    Negative Logits
     Manufacturer
    -0.74
    steen
    -0.74
    fare
    -0.73
    spring
    -0.71
    gio
    -0.67
    rpm
    -0.67
     Kers
    -0.66
     Rove
    -0.65
    hower
    -0.65
     Lans
    -0.64
    POSITIVE LOGITS
    gender
    1.15
     transgender
    0.98
     transsexual
    0.97
    sexual
    0.94
     genital
    0.88
     genders
    0.85
     gender
    0.84
     restroom
    0.81
     bathroom
    0.80
    ethnic
    0.80
    Activations Density 0.012%

    No Known Activations