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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 1190
    Prev
    Next
    INDEX
    Explanations

    words related to the transgender community

    oai_token-act-pair · gpt-3.5-turbo

    references to transgender topics and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Slug
    -0.81
     WARRANT
    -0.70
     Hearts
    -0.68
    FIELD
    -0.68
     Freeze
    -0.65
    RANT
    -0.64
     Sunder
    -0.64
     Wass
    -0.64
     Fool
    -0.64
    eers
    -0.63
    POSITIVE LOGITS
    mitt
    1.19
    continental
    1.09
    gression
    1.09
    racial
    1.04
    missible
    1.03
    istors
    1.01
    posed
    0.99
    position
    0.96
    posing
    0.96
    figured
    0.95
    Activations Density 0.007%

    No Known Activations