© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 13419
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific people or proper nouns, with a focus on the name "Milton Friedman."

    oai_token-act-pair · gpt-3.5-turbo

    references to the economist Milton Friedman

    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
    taboola
    -0.84
    ebook
    -0.73
    members
    -0.71
    */(
    -0.71
    ¿
    -0.69
    vity
    -0.69
    esthetic
    -0.68
    loads
    -0.67
    SHIP
    -0.66
    Member
    -0.66
    POSITIVE LOGITS
     Keynes
    1.37
     Milton
    1.14
     Friedman
    1.05
     Bradley
    0.89
     Faul
    0.87
     Vaughan
    0.82
    shire
    0.82
     Mandela
    0.80
     Nelson
    0.77
    eco
    0.71
    Activations Density 0.009%

    No Known Activations