© 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. 660
    Prev
    Next
    INDEX
    Explanations

    sources and citations

    oai_token-act-pair · gpt-3.5-turbo

    sources or references cited in the text

    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
    mble
    -0.93
    anooga
    -0.92
    wagen
    -0.85
    igue
    -0.76
    joice
    -0.73
    issan
    -0.73
     depended
    -0.73
    ĪĴ
    -0.72
    odox
    -0.72
    oshenko
    -0.72
    POSITIVE LOGITS
     ???
    0.87
     Nex
    0.78
     IR
    0.76
     Article
    0.75
     Medline
    0.75
     Cosponsors
    0.75
     Xin
    0.75
     NIH
    0.74
     Om
    0.73
     TBD
    0.72
    Activations Density 0.035%

    No Known Activations