© 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. 8-RES-JB
    11. 2525
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals or names

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly those in the entertainment industry

    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
    ruary
    -0.74
     Akin
    -0.71
    theless
    -0.69
     orphans
    -0.66
     Moroccan
    -0.62
     representation
    -0.62
     Laos
    -0.61
     preservation
    -0.61
     hospitality
    -0.59
     Dak
    -0.59
    POSITIVE LOGITS
    kov
    0.81
    andowski
    0.74
    angan
    0.74
    agan
    0.73
    agi
    0.71
    henko
    0.70
    oyal
    0.70
    Ĥ¬
    0.69
    emort
    0.69
    attr
    0.69
    Activations Density 0.161%

    No Known Activations