Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 8125
    Prev
    Next
    INDEX
    Explanations

    words related to a specific medical condition or treatment

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Zanesville."

    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
    itude
    -0.85
    mie
    -0.80
    ECH
    -0.78
    ãĤ³
    -0.72
    DOC
    -0.68
     Thatcher
    -0.67
    è¦ļéĨĴ
    -0.67
    urtles
    -0.65
    INC
    -0.65
    ORY
    -0.65
    POSITIVE LOGITS
    thood
    0.86
    ragon
    0.82
    walker
    0.80
    iewicz
    0.77
    ayer
    0.75
    layer
    0.75
    elaide
    0.75
    ayers
    0.75
    perm
    0.73
    xual
    0.72
    Activations Density 0.011%

    No Known Activations