© 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. 4-RES-JB
    11. 7308
    Prev
    Next
    INDEX
    Explanations

    references to specific web page interactions and instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific pages or sections within a document or platform

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

    No Comments

    Negative Logits
    ALLY
    -0.77
    CAST
    -0.77
     Instruments
    -0.72
    creen
    -0.69
     Franch
    -0.66
    borgh
    -0.64
    xon
    -0.64
    Rated
    -0.63
    kowski
    -0.62
    igham
    -0.62
    POSITIVE LOGITS
    antry
    1.39
    pages
    1.09
    views
    1.09
    page
    0.87
     page
    0.84
     pages
    0.81
    earance
    0.80
    lists
    0.76
    ants
    0.76
    unks
    0.75
    Activations Density 0.018%

    No Known Activations