© 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. 0-RES-JB
    11. 13802
    Prev
    Next
    INDEX
    Explanations

    names of a specific person, "Stanton"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their statements or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cycl
    -0.79
    Oracle
    -0.76
    yip
    -0.74
    iw
    -0.70
     NEC
    -0.68
    imes
    -0.67
    ables
    -0.66
    BOOK
    -0.64
     commun
    -0.63
     audible
    -0.63
    POSITIVE LOGITS
     Stam
    2.08
    sta
    1.92
     Stri
    1.86
     Stanton
    1.82
     Sta
    1.79
     Starr
    1.73
     Stuart
    1.45
     Stacy
    1.38
     Lund
    1.38
     Stick
    1.36
    Activations Density 0.058%

    No Known Activations