© 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. 6-RES-JB
    11. 16891
    Prev
    Next
    INDEX
    Explanations

    news outlets or publications

    oai_token-act-pair · gpt-3.5-turbo

    mentions of news sources or types of news-related content

    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
    ãĤ©
    -0.83
    oiler
    -0.79
    reenshot
    -0.75
    vertisements
    -0.66
     blur
    -0.65
     crop
    -0.63
    =-=-=-=-
    -0.61
     filler
    -0.61
    ................................................................
    -0.60
    arov
    -0.60
    POSITIVE LOGITS
    Chem
    0.99
    Gold
    0.91
    Games
    0.89
    swers
    0.87
    elaide
    0.85
    Site
    0.84
    DX
    0.82
    doms
    0.82
    west
    0.81
    Textures
    0.81
    Activations Density 0.178%

    No Known Activations