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. 11-RES-JB
    6. 3013
    Prev
    Next
    INDEX
    Explanations

    information related to women's rights and gender equality

    oai_token-act-pair · gpt-3.5-turbo

    references to women and their rights in various contexts

    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
    raltar
    -0.81
    REDACTED
    -0.79
    eme
    -0.73
     Flavoring
    -0.72
    ebus
    -0.70
    asper
    -0.68
    EMA
    -0.68
    æĸ¹
    -0.68
    ellation
    -0.67
    adelphia
    -0.67
    POSITIVE LOGITS
    folk
    1.21
     empowerment
    1.07
    opausal
    1.01
     entrepreneurs
    0.96
     genital
    0.93
     singers
    0.90
     reproductive
    0.89
     supremacists
    0.86
    's
    0.85
    hood
    0.85
    Activations Density 0.077%

    No Known Activations