© 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. 1-RES-JB
    11. 645
    Prev
    Next
    INDEX
    Explanations

    references to the term "Wiki" at various activation levels

    oai_token-act-pair · gpt-3.5-turbo

    references to various wikis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ordial
    -0.73
    Interstitial
    -0.73
    uctor
    -0.71
    female
    -0.67
    gm
    -0.65
    NetMessage
    -0.64
    irds
    -0.64
    aths
    -0.63
    orous
    -0.62
     Pall
    -0.62
    POSITIVE LOGITS
    wiki
    1.30
     Wiki
    0.99
    hack
    0.91
     wik
    0.91
     wiki
    0.89
    ipedia
    0.89
    ileaks
    0.88
    Leaks
    0.87
     encyclopedia
    0.86
    Wiki
    0.85
    Activations Density 0.010%

    No Known Activations