© 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. 20765
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and industry

    oai_token-act-pair · gpt-3.5-turbo

    nouns and terms related to animals, economics, and social issues

    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
    代
    -0.63
    DonaldTrump
    -0.62
     Azerb
    -0.53
    cair
    -0.52
     disadvant
    -0.52
     Nare
    -0.52
    nesday
    -0.51
    ãĤ´ãĥ³
    -0.50
    weeney
    -0.50
    swick
    -0.49
    POSITIVE LOGITS
     alike
    1.11
     versa
    0.57
    cellaneous
    0.51
     thereof
    0.50
     industries
    0.49
     respectively
    0.49
     exposures
    0.48
     âĢº
    0.44
    natureconservancy
    0.43
    utterstock
    0.43
    Activations Density 0.665%

    No Known Activations