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. 6-RES-JB
    6. 2435
    Prev
    Next
    INDEX
    Explanations

    references to web development or web applications

    oai_token-act-pair · gpt-3.5-turbo

    references to web-related topics and technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    士
    -0.70
     Clause
    -0.69
     Lauder
    -0.68
     Mori
    -0.68
     unfocusedRange
    -0.66
     Cla
    -0.63
    xual
    -0.63
    baugh
    -0.62
     Naz
    -0.62
     Bened
    -0.59
    POSITIVE LOGITS
    inar
    1.11
    pages
    1.06
    izen
    1.04
     browsers
    0.96
    browser
    0.95
    masters
    0.90
     browser
    0.87
    Socket
    0.86
    bing
    0.85
    master
    0.85
    Activations Density 0.015%

    No Known Activations