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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 7014
    Prev
    Next
    INDEX
    Explanations

    phrases relating to transgender rights, specifically in the context of restroom usage

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to gender identity and restroom usage policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cheap
    -0.85
     looting
    -0.83
     Warranty
    -0.79
     antitrust
    -0.76
     FEMA
    -0.74
     bribe
    -0.71
     Yelp
    -0.70
     Faul
    -0.70
     Nit
    -0.68
     Prices
    -0.67
    POSITIVE LOGITS
     transsexual
    1.53
     gender
    1.49
     transgender
    1.46
    gender
    1.45
    Gender
    1.45
     genders
    1.39
     pronouns
    1.35
     Transgender
    1.33
     Gender
    1.33
     chromosomes
    1.30
    Activations Density 0.423%

    No Known Activations