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. 20697
    Prev
    Next
    INDEX
    Explanations

    words related to the Italian word "Stella" or similar variations like "stella," "stroller," or "stellar."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "lla" in various contexts

    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
    OUN
    -0.63
     defensive
    -0.62
     Fram
    -0.59
    ifications
    -0.58
     corner
    -0.58
     ratings
    -0.57
     desk
    -0.56
     upt
    -0.56
     49
    -0.56
     prospective
    -0.55
    POSITIVE LOGITS
    lla
    4.64
    llo
    2.37
    lli
    2.32
    ll
    1.95
    lly
    1.71
    llan
    1.59
    tta
    1.44
    tti
    1.31
    ller
    1.29
    lled
    1.23
    Activations Density 0.017%

    No Known Activations