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. 1-RES-JB
    6. 5639
    Prev
    Next
    INDEX
    Explanations

    specific references to directories and paths in a technical context

    oai_token-act-pair · gpt-3.5-turbo

    references to file system directories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acted
    -0.92
    rained
    -0.85
    acting
    -0.85
    uca
    -0.84
    arching
    -0.70
    rg
    -0.69
    hem
    -0.68
    eat
    -0.68
    gotten
    -0.67
    gr
    -0.65
    POSITIVE LOGITS
     directory
    1.28
     directories
    1.20
     Directory
    0.99
    ãĤ¼ãĤ¦ãĤ¹
    0.99
    directory
    0.95
     filesystem
    0.86
    Directory
    0.85
     listings
    0.84
     descriptor
    0.81
     folder
    0.77
    Activations Density 0.008%

    No Known Activations