© 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. 6-RES-JB
    11. 10692
    Prev
    Next
    INDEX
    Explanations

    terms related to covering or discussing specific topics in articles

    oai_token-act-pair · gpt-3.5-turbo

    references to previous articles or columns written by the author

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cho
    -0.70
     ric
    -0.68
     ripple
    -0.67
     Loch
    -0.66
    BuyableInstoreAndOnline
    -0.64
     cogn
    -0.64
     Corinth
    -0.63
     Canaveral
    -0.62
     helicopter
    -0.61
     Lauder
    -0.61
    POSITIVE LOGITS
    endix
    0.90
     "$:/
    0.89
    escription
    0.87
    ODUCT
    0.81
    Introduction
    0.80
    RFC
    0.79
    uploads
    0.78
    href
    0.76
    otes
    0.73
    nesday
    0.73
    Activations Density 0.426%

    No Known Activations