© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 3119
    Prev
    Next
    INDEX
    Explanations

    names of politicians and political figures

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and titles associated with individuals or entities

    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
    nesday
    -0.72
    luster
    -0.61
    glers
    -0.60
    ancial
    -0.60
    eatures
    -0.60
    aukee
    -0.57
     rul
    -0.56
    wcs
    -0.56
     ail
    -0.56
     remem
    -0.55
    POSITIVE LOGITS
    ansas
    0.79
    inian
    0.74
    ondo
    0.73
    itect
    0.69
    eta
    0.67
    rary
    0.66
     Fatal
    0.65
    Spoiler
    0.65
     Schwarzenegger
    0.64
    eli
    0.64
    Activations Density 0.071%

    No Known Activations