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. 3-RES-JB
    6. 7546
    Prev
    Next
    INDEX
    Explanations

    the word "of" within various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around the concept of "thinking about" and "considering" various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ante
    -0.77
    edition
    -0.68
     reminders
    -0.67
     declared
    -0.66
     reminder
    -0.63
    owed
    -0.61
    ounty
    -0.60
    owl
    -0.60
    pite
    -0.60
    }{
    -0.57
    POSITIVE LOGITS
     aloud
    0.77
     guiActiveUnfocused
    0.73
    agall
    0.70
    Ͻ
    0.70
    umar
    0.66
    ahime
    0.66
    Õ
    0.65
    uchi
    0.65
    acles
    0.63
    igraph
    0.63
    Activations Density 0.183%

    No Known Activations