Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 24238
    Prev
    Next
    INDEX
    Explanations

    names related to Jason

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Jason."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ship
    -0.80
    iments
    -0.77
    Reviewer
    -0.69
    cess
    -0.67
    ega
    -0.64
    esta
    -0.63
    minist
    -0.63
    gary
    -0.62
    gra
    -0.62
    ences
    -0.61
    POSITIVE LOGITS
     Chaff
    0.99
     Bour
    0.93
     Kidd
    0.91
     Blossom
    0.84
     Grill
    0.83
     Kessler
    0.79
     Garrett
    0.79
     Vor
    0.78
     Mew
    0.76
     Ald
    0.75
    Activations Density 0.028%

    No Known Activations