© 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 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. 1814
    Prev
    Next
    INDEX
    Explanations

    paragraphs ending with a question or discussion prompt

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that indicate a call to action or additional reading related to various topics

    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
     oun
    -0.66
    mbuds
    -0.64
    urch
    -0.64
     Morty
    -0.63
     inspecting
    -0.62
    ioch
    -0.61
     supervised
    -0.60
     contrace
    -0.60
     lifes
    -0.59
     shove
    -0.59
    POSITIVE LOGITS
    Tags
    0.83
    Woman
    0.75
    Comments
    0.74
    Comment
    0.73
    Original
    0.73
    Recent
    0.73
    Watch
    0.72
    BOOK
    0.69
    âĻ¦
    0.68
    *
    0.68
    Activations Density 0.075%

    No Known Activations