© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 3829
    Prev
    Next
    INDEX
    Explanations

    URLs and email addresses

    oai_token-act-pair · gpt-3.5-turbo

    references to media websites and their URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Schne
    -0.65
    osponsors
    -0.64
     manual
    -0.64
    tein
    -0.64
     Lauder
    -0.62
     Tsukuyomi
    -0.62
     joke
    -0.62
     treason
    -0.61
     latent
    -0.60
     interchangeable
    -0.59
    POSITIVE LOGITS
    com
    1.02
    org
    0.90
    co
    0.89
    biz
    0.88
    apple
    0.86
    nl
    0.75
    wordpress
    0.74
    yahoo
    0.74
     Retrieved
    0.73
    info
    0.73
    Activations Density 0.047%

    No Known Activations