© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 18334
    Prev
    Next
    INDEX
    Explanations

    URLs, specifically identifying the presence of 'www' in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to websites, particularly those containing "www."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     expulsion
    -0.65
     Ballard
    -0.61
     Pearce
    -0.60
     handling
    -0.60
     Townsend
    -0.59
     forcefully
    -0.59
     quart
    -0.59
     packing
    -0.59
     inadequ
    -0.58
     dispens
    -0.58
    POSITIVE LOGITS
    www
    1.25
    youtu
    1.03
    natureconservancy
    1.01
    forum
    1.00
    ://
    0.97
    ctl
    0.94
    forums
    0.91
     www
    0.90
    ww
    0.90
    sites
    0.89
    Activations Density 0.013%

    No Known Activations