© 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. 11207
    Prev
    Next
    INDEX
    Explanations

    URLs or hyperlinks starting with "https://" or "http://"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of URLs and web links in the text

    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
     dwar
    -0.73
     recl
    -0.70
     doom
    -0.69
     roomm
    -0.66
     secretaries
    -0.65
     prepar
    -0.64
     utility
    -0.64
     adversaries
    -0.64
     Merchants
    -0.64
     Guid
    -0.63
    POSITIVE LOGITS
    twitter
    1.21
    youtu
    1.19
    t
    1.14
    imgur
    1.05
     VIDEOS
    0.96
    Twitter
    0.95
    ://
    0.95
    pic
    0.93
    goo
    0.93
    TED
    0.92
    Activations Density 0.032%

    No Known Activations