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. 9000
    Prev
    Next
    INDEX
    Explanations

    references to the operating system "Windows XP."

    oai_token-act-pair · gpt-3.5-turbo

    references to the Windows XP operating system

    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
    aber
    -0.68
    iberal
    -0.66
     Marshall
    -0.65
    ás
    -0.65
    mond
    -0.64
     solicitor
    -0.64
    ack
    -0.63
    rist
    -0.63
    azar
    -0.62
    Attorney
    -0.62
    POSITIVE LOGITS
     XP
    3.79
    XP
    2.71
     xp
    2.23
    xp
    1.57
     Vista
    1.47
     EXP
    1.22
     HP
    1.15
     NX
    1.05
     PCs
    1.02
     XML
    1.00
    Activations Density 0.012%

    No Known Activations