© 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. 4-RES-JB
    11. 17106
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to educational institutions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific educational institutions, particularly Cornell and Temple Universities

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

    No Comments

    Negative Logits
    ipper
    -0.80
    hire
    -0.79
    entimes
    -0.75
    odic
    -0.74
    orter
    -0.73
    iasm
    -0.73
    ombies
    -0.71
    glomer
    -0.69
    arbon
    -0.69
    ortal
    -0.69
    POSITIVE LOGITS
     Cornell
    0.83
     Haas
    0.79
     Milk
    0.74
    ighton
    0.72
     Davis
    0.69
     Triangle
    0.67
     McGill
    0.67
    ANCE
    0.67
    fing
    0.67
     Heights
    0.66
    Activations Density 0.024%

    No Known Activations