© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 10059
    Prev
    Next
    INDEX
    Explanations

    references to different generations, such as Baby Boomers and Millennials

    oai_token-act-pair · gpt-3.5-turbo

    references to generational labels, specifically "Millennials" and "Generation 9"

    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
    amina
    -0.99
    aleigh
    -0.84
    yer
    -0.79
    abl
    -0.75
    eneg
    -0.73
    abre
    -0.73
    pmwiki
    -0.73
    ern
    -0.69
    querque
    -0.69
    esar
    -0.67
    POSITIVE LOGITS
     generation
    0.92
     inher
    0.89
    naire
    0.86
     Generations
    0.86
     generations
    0.81
     generational
    0.78
     gap
    0.78
     Generation
    0.76
     inherited
    0.71
     inherit
    0.69
    Activations Density 0.045%

    No Known Activations