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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 20236
    Prev
    Next
    INDEX
    Explanations

    terms related to reports, interviews, and documentation

    oai_token-act-pair · gpt-3.5-turbo

    connections between various reports and accounts in news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.87
    itans
    -0.79
    aires
    -0.78
     disadvantaged
    -0.77
    hei
    -0.70
     dwarves
    -0.70
    anooga
    -0.68
    advant
    -0.68
    ó
    -0.67
    ampires
    -0.67
    POSITIVE LOGITS
     interviews
    1.05
     subsequent
    1.01
     statements
    0.98
     unpublished
    0.96
     transcripts
    0.95
     accompanying
    0.94
     screenshots
    0.94
     excerpts
    0.92
     filings
    0.91
     Statements
    0.88
    Activations Density 0.458%

    No Known Activations