© 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. 9-RES-JB
    11. 11737
    Prev
    Next
    INDEX
    Explanations

    references to financial values and figures

    oai_token-act-pair · gpt-3.5-turbo

    sequences of text where the text starts and ends with a specific token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edin
    -0.78
    Daddy
    -0.72
    ieu
    -0.69
    Loading
    -0.65
    AIR
    -0.63
    undo
    -0.63
    antics
    -0.62
    anni
    -0.62
    FB
    -0.62
    Shop
    -0.59
    POSITIVE LOGITS
     abbre
    0.92
     successor
    0.90
     slang
    0.74
     genus
    0.72
     decentralized
    0.72
     leader
    0.69
     nonpartisan
    0.68
     noun
    0.68
     symbol
    0.67
     translator
    0.66
    Activations Density 0.155%

    No Known Activations