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. 7-RES-JB
    6. 4579
    Prev
    Next
    INDEX
    Explanations

    the word "Sch" followed by a number ranging from 8 to 10

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Sch" or related variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.89
     censored
    -0.66
     Korra
    -0.66
     Xin
    -0.66
     constrained
    -0.66
     reborn
    -0.64
    ãĥ¼ãĥĨãĤ£
    -0.63
     responsible
    -0.63
     futures
    -0.63
     Tibetan
    -0.62
    POSITIVE LOGITS
    izoph
    1.29
    izophren
    1.21
    utz
    1.21
    acht
    1.13
    umann
    1.10
    nee
    1.10
    afer
    1.09
    uler
    1.09
    mitt
    1.08
    ulz
    1.08
    Activations Density 0.020%

    No Known Activations