© 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. 10-RES-JB
    11. 20623
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'document' in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.79
    cffff
    -0.78
    awar
    -0.69
    NetMessage
    -0.69
    cffffcc
    -0.68
    ntil
    -0.68
     Osw
    -0.67
    dden
    -0.65
    @#&
    -0.64
    ategory
    -0.64
    POSITIVE LOGITS
    arians
    1.21
    arian
    1.11
     detailing
    1.03
     outlining
    1.02
     documents
    1.00
    aries
    0.94
    ually
    0.93
     document
    0.93
     documenting
    0.92
     pertaining
    0.90
    Activations Density 0.044%

    No Known Activations