© 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. 11-RES-JB
    11. 11821
    Prev
    Next
    INDEX
    Explanations

    words related to legal, financial, and official documentation

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or official documents and their requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Orchestra
    -0.75
     Galile
    -0.70
    tackle
    -0.68
    deep
    -0.68
    aughs
    -0.67
    onomous
    -0.64
    adj
    -0.63
    姫
    -0.63
    cffff
    -0.62
     Transform
    -0.62
    POSITIVE LOGITS
     verifying
    1.28
     documenting
    1.20
     electronically
    1.20
     detailing
    1.12
     filed
    1.11
     mailed
    1.11
     proving
    1.06
     photoc
    1.06
     affidavit
    1.05
     fax
    1.04
    Activations Density 0.288%

    No Known Activations