© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 1613
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development, such as "blog post," "mail," "install," and "package."

    oai_token-act-pair · gpt-3.5-turbo

    references to blog posts and their related technical discussions or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.93
    advertising
    -0.83
     telev
    -0.80
     dishes
    -0.76
     wardrobe
    -0.71
    mouth
    -0.71
     television
    -0.69
    drug
    -0.68
    Bey
    -0.68
     complexion
    -0.66
    POSITIVE LOGITS
     github
    1.25
     GitHub
    1.24
     RFC
    1.12
     Github
    1.12
     linux
    1.11
     :-)
    1.09
     debian
    1.07
     gcc
    1.05
    github
    1.03
     Qt
    1.03
    Activations Density 0.907%

    No Known Activations