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. 0-RES-JB
    6. 21313
    Prev
    Next
    INDEX
    Explanations

    words that end with the suffix "-um"

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of "iums" and "orums"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.56
     shares
    -0.56
     acknow
    -0.56
     affiliated
    -0.55
     stocking
    -0.55
     carve
    -0.55
     date
    -0.54
     stripping
    -0.54
     rend
    -0.53
    >>>>
    -0.53
    POSITIVE LOGITS
    um
    4.28
    ums
    2.77
    UM
    2.33
    uman
    1.61
    umm
    1.58
    ume
    1.57
    uma
    1.56
    umn
    1.54
    orum
    1.48
    umar
    1.48
    Activations Density 0.019%

    No Known Activations