© 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. 1-RES-JB
    11. 23010
    Prev
    Next
    INDEX
    Explanations

    names of people, especially those with Scandinavian origins

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly of individuals, specifically those associated with sports or entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agents
    -0.87
    urses
    -0.77
    lished
    -0.72
    recomm
    -0.70
    smoking
    -0.66
    attled
    -0.66
    mediate
    -0.64
    attery
    -0.64
     PowerPoint
    -0.64
    oured
    -0.64
    POSITIVE LOGITS
     Lars
    1.18
     Larson
    0.99
     Magnus
    0.97
     challeng
    0.87
     Anders
    0.85
     Luthor
    0.84
     Markus
    0.83
     Pengu
    0.82
     Sven
    0.81
     horizont
    0.81
    Activations Density 0.012%

    No Known Activations