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. 10-RES-JB
    6. 14884
    Prev
    Next
    INDEX
    Explanations

    phrases related to demographics and statistics, specifically focusing on people, women, and age groups

    oai_token-act-pair · gpt-3.5-turbo

    references to demographics and specific groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tainment
    -1.06
    rawdownloadcloneembedreportprint
    -0.82
    bows
    -0.82
    rament
    -0.77
    apixel
    -0.76
    ãĥķãĤ©
    -0.75
    aughs
    -0.74
    ãģĨ
    -0.73
    æĪ¦
    -0.70
    acebook
    -0.67
    POSITIVE LOGITS
     eligible
    1.24
     who
    1.21
     enrolled
    1.19
     undergoing
    1.16
     diagnosed
    1.16
     wishing
    1.15
     aged
    1.15
     experiencing
    1.14
     intending
    1.12
     born
    1.11
    Activations Density 0.230%

    No Known Activations