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

    Neuronpedia

    APICircuit 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. 4-RES-JB
    6. 21530
    Prev
    Next
    INDEX
    Explanations

    terms related to gender identity and diversity

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to gender identity and expression

    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
    }}}
    -0.75
    æ©Ł
    -0.72
     rake
    -0.68
    Completed
    -0.68
     Eternity
    -0.66
    akings
    -0.66
    hao
    -0.65
    UNCH
    -0.62
    Construction
    -0.61
    çīĪ
    -0.61
    POSITIVE LOGITS
     lesbian
    0.95
     lesbians
    0.95
     patriarchy
    0.84
     feminism
    0.82
    femin
    0.79
    marriage
    0.79
     Lesbian
    0.78
     feminist
    0.78
     shaming
    0.78
     unmarried
    0.77
    Activations Density 0.420%

    No Known Activations