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. 10-RES-JB
    6. 1551
    Prev
    Next
    INDEX
    Explanations

    instances of the word "semicolon"

    oai_token-act-pair · gpt-3.5-turbo

    references to "semesters" or the concept of semesters in an educational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¸ı
    -0.63
     ramps
    -0.61
    Adds
    -0.60
     Strauss
    -0.59
     otherwise
    -0.58
     foremost
    -0.58
     stock
    -0.57
    houses
    -0.57
     delight
    -0.57
    hered
    -0.56
    POSITIVE LOGITS
    inary
    1.48
    antics
    1.45
    inar
    1.32
    antic
    1.30
    blance
    1.26
    iotics
    1.24
    pai
    1.18
    itone
    1.13
    antically
    1.11
    igroup
    1.11
    Activations Density 0.017%

    No Known Activations