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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 20301
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people, places, and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     feds
    -0.62
     Saudis
    -0.62
    urtles
    -0.61
     organizers
    -0.61
     anarchists
    -0.61
    quickShipAvailable
    -0.60
     Europeans
    -0.59
     prostitutes
    -0.59
     cleaner
    -0.57
     physicists
    -0.57
    POSITIVE LOGITS
    's
    1.15
    ÃŃs
    0.98
    ´
    0.83
    \'
    0.81
     bloodstream
    0.78
    `
    0.72
    Ê
    0.72
    speak
    0.71
     territory
    0.70
     favour
    0.69
    Activations Density 0.533%

    No Known Activations