© 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. 11-RES-JB
    11. 22446
    Prev
    Next
    INDEX
    Explanations

    the phrase "of Man"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific movies and characters in pop culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.91
    cffff
    -0.78
     Yug
    -0.76
    iety
    -0.74
    agall
    -0.74
    icago
    -0.74
    yna
    -0.73
    astern
    -0.72
    heast
    -0.71
    abases
    -0.71
    POSITIVE LOGITS
     Man
    2.05
     Men
    1.79
    Man
    1.74
     MAN
    1.67
     man
    1.61
    Men
    1.54
     men
    1.51
    MAN
    1.45
    man
    1.44
     Woman
    1.35
    Activations Density 0.326%

    No Known Activations