© 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. 10-RES-JB
    11. 5431
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    legal references and sections related to laws and regulations

    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
    ciating
    -0.68
     Guinness
    -0.63
     ç¥ŀ
    -0.63
     Reborn
    -0.62
     Solitaire
    -0.62
    spot
    -0.62
     Carly
    -0.59
     Raphael
    -0.59
     anonymously
    -0.58
     Morning
    -0.58
    POSITIVE LOGITS
    )(
    1.26
     subdivision
    1.02
    iii
    0.85
    ));
    0.84
     subsection
    0.84
     subsections
    0.82
    xi
    0.80
     seq
    0.78
    )).
    0.77
     subparagraph
    0.77
    Activations Density 0.036%

    No Known Activations