© 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. 2-RES-JB
    11. 1545
    Prev
    Next
    INDEX
    Explanations

    mentions and descriptions of specific events, people, or places

    oai_token-act-pair · gpt-3.5-turbo

    references to key figures or events in political and social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Starcraft
    -0.58
     cosmos
    -0.58
    âĻ¥
    -0.52
     ze
    -0.52
    Transform
    -0.52
     imaginary
    -0.52
     melanch
    -0.51
    laughs
    -0.51
     Clockwork
    -0.51
    !).
    -0.51
    POSITIVE LOGITS
     briefed
    0.72
    enegger
    0.69
    nesty
    0.65
     spokeswoman
    0.65
    arnaev
    0.64
     blamed
    0.64
     bolstered
    0.63
     alarmed
    0.63
     halted
    0.62
     spokesman
    0.62
    Activations Density 4.212%

    No Known Activations