© 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. 6-RES-JB
    11. 9349
    Prev
    Next
    INDEX
    Explanations

    references to legal acts and legislative documents

    oai_token-act-pair · gpt-3.5-turbo

    references to legal acts and legislation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edin
    -0.78
    rosse
    -0.77
    ibo
    -0.70
     onlook
    -0.67
    scenes
    -0.66
     Wand
    -0.66
     Nanto
    -0.65
    pi
    -0.64
    ordinate
    -0.63
     throats
    -0.63
    POSITIVE LOGITS
     ratified
    1.18
     repealed
    1.08
     Amendments
    0.93
     binding
    0.92
     enacted
    0.90
     invoked
    0.89
     promulg
    0.88
     constitution
    0.86
     legalized
    0.86
     rewritten
    0.86
    Activations Density 0.482%

    No Known Activations