Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 8697
    Prev
    Next
    INDEX
    Explanations

    names of famous people, especially celebrities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly the names of notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llah
    -0.75
    angan
    -0.72
    iate
    -0.71
    ial
    -0.70
    wi
    -0.70
    ood
    -0.70
    arter
    -0.69
    raq
    -0.68
    irm
    -0.68
    iences
    -0.68
    POSITIVE LOGITS
     Manson
    1.33
     Monroe
    0.89
     Elvis
    0.87
     Marilyn
    0.77
    azine
    0.75
     Osw
    0.71
     Spice
    0.70
     Pres
    0.70
    swick
    0.70
    osaurs
    0.68
    Activations Density 0.013%

    No Known Activations