© 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. 8-RES-JB
    11. 11406
    Prev
    Next
    INDEX
    Explanations

    information related to legal documents, government services, and educational programs

    oai_token-act-pair · gpt-3.5-turbo

    legal and official documents or records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grinning
    -0.83
     Despair
    -0.83
     torment
    -0.80
     damned
    -0.77
     uncanny
    -0.77
     fuck
    -0.76
     Frankenstein
    -0.76
     banging
    -0.76
     Eliot
    -0.75
     overpower
    -0.75
    POSITIVE LOGITS
     Browse
    1.13
    Information
    1.12
     Regulations
    1.09
     Availability
    1.05
     FAQ
    1.01
    requently
    1.01
     Choose
    0.97
     Registration
    0.97
     Locations
    0.96
    Services
    0.96
    Activations Density 0.657%

    No Known Activations