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. 4-RES-JB
    6. 5782
    Prev
    Next
    INDEX
    Explanations

    references to the name "Quinn"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Quinn."

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

    No Comments

    Negative Logits
    ãĤ·ãĥ£
    -0.77
    ¶æ
    -0.70
    xual
    -0.70
     fuels
    -0.70
     welf
    -0.68
    ochond
    -0.67
     marrow
    -0.66
     pts
    -0.64
     fuel
    -0.64
     mileage
    -0.63
    POSITIVE LOGITS
     Quinn
    0.98
    ipeg
    0.93
    lich
    0.92
    spir
    0.90
    stown
    0.81
    pei
    0.79
    ite
    0.78
    icut
    0.77
    gren
    0.77
    itic
    0.76
    Activations Density 0.009%

    No Known Activations