© 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. 3-RES-JB
    11. 647
    Prev
    Next
    INDEX
    Explanations

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

    oai_token-act-pair · gpt-3.5-turbo

    URLs and web addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sided
    -0.75
     Palestin
    -0.74
     confir
    -0.73
    ©¶æ
    -0.71
     conclud
    -0.70
     Morse
    -0.70
     Labrador
    -0.70
    ĺħ
    -0.69
     dispatched
    -0.68
     taxp
    -0.68
    POSITIVE LOGITS
    www
    1.61
    natureconservancy
    1.44
    ://
    1.37
    docs
    1.08
    past
    1.07
    archive
    1.07
    localhost
    1.01
    wcsstore
    1.00
    goo
    1.00
    :/
    1.00
    Activations Density 0.013%

    No Known Activations