© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20777
    Prev
    Next
    INDEX
    Explanations

    keywords related to the internet and networking

    oai_token-act-pair · gpt-3.5-turbo

    references to "net" related concepts, particularly concerning net migration and net neutrality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hips
    -0.70
     Judd
    -0.66
     Pend
    -0.64
     Derek
    -0.61
     Abe
    -0.60
     Alb
    -0.60
     Alam
    -0.59
     Oro
    -0.58
     Randolph
    -0.57
     Fraz
    -0.57
    POSITIVE LOGITS
    anyahu
    1.60
    izens
    1.51
    izen
    1.32
    tle
    1.28
    iquette
    1.27
    flix
    1.18
     neutrality
    1.18
    roots
    1.14
    ting
    1.13
    working
    1.13
    Activations Density 0.038%

    No Known Activations