© 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. 10-RES-JB
    11. 18747
    Prev
    Next
    INDEX
    Explanations

    technical terms related to technology and research

    oai_token-act-pair · gpt-3.5-turbo

    information related to advanced technologies and their applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Franch
    -0.88
     welf
    -0.73
     Equity
    -0.69
     eg
    -0.69
    )/
    -0.69
     FTA
    -0.67
     Spons
    -0.66
     Cabin
    -0.64
    ~~~~
    -0.64
     ie
    -0.63
    POSITIVE LOGITS
     pinpoint
    0.91
     undet
    0.90
     detectable
    0.89
     microscopic
    0.87
     scientists
    0.82
     Hawking
    0.82
    Scientists
    0.79
     astronomers
    0.77
    DNA
    0.76
     crucial
    0.76
    Activations Density 0.576%

    No Known Activations