© 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. 7876
    Prev
    Next
    INDEX
    Explanations

    notifications about enabling JavaScript or viewing comments in websites

    oai_token-act-pair · gpt-3.5-turbo

    references to JavaScript and comment viewing functionality in web content

    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
     whistle
    -0.71
     exerc
    -0.60
     Id
    -0.58
     ann
    -0.57
     exp
    -0.56
     Glob
    -0.53
     Revis
    -0.52
     perm
    -0.52
     Immunity
    -0.51
     Hudson
    -0.51
    POSITIVE LOGITS
    ighth
    0.73
    thumbnails
    0.69
    qus
    0.68
    iffe
    0.67
    interstitial
    0.66
    rencies
    0.66
     isEnabled
    0.65
    æ©
    0.63
    Asset
    0.63
    agra
    0.63
    Activations Density 0.044%

    No Known Activations