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. 9-RES-JB
    6. 21413
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming concepts, such as data manipulation, pointers, construction, and memory structures

    oai_token-act-pair · gpt-3.5-turbo

    references to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Professional
    -0.73
     Journalism
    -0.70
    India
    -0.70
    Website
    -0.70
    Technology
    -0.68
     bloggers
    -0.67
    conom
    -0.67
     professionally
    -0.67
     professionals
    -0.67
     professional
    -0.66
    POSITIVE LOGITS
     duplicate
    1.03
     incre
    1.02
     adjacent
    1.01
     consecut
    1.00
     skipped
    0.93
     remaining
    0.93
     discard
    0.93
     successive
    0.93
     versa
    0.92
     consecutive
    0.92
    Activations Density 0.624%

    No Known Activations