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. 22652
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Shel" or "Ske"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "skeletal" and its variations, likely associated with discussions of skeletal structures or conditions

    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
    icip
    -0.70
    ending
    -0.69
    ensical
    -0.69
    ends
    -0.65
    alg
    -0.65
     showers
    -0.64
    orus
    -0.62
    ended
    -0.61
    cake
    -0.60
    give
    -0.60
    POSITIVE LOGITS
    wered
    1.21
    letal
    1.16
    leton
    1.15
    pta
    1.06
    lled
    0.95
    wed
    0.93
    lling
    0.92
    ETS
    0.87
    gow
    0.85
    bridge
    0.84
    Activations Density 0.064%

    No Known Activations