© 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. 20815
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and controversies

    oai_token-act-pair · gpt-3.5-turbo

    references to legal matters and judgments

    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
     renaissance
    -0.75
     nostalg
    -0.74
     Flavoring
    -0.71
     ðŁĻĤ
    -0.70
     rejoice
    -0.69
     optim
    -0.69
     innov
    -0.68
     ourselves
    -0.67
     eagerly
    -0.67
     ageing
    -0.66
    POSITIVE LOGITS
    Prosecutors
    1.16
     prosecutors
    1.14
     prosecut
    1.10
     incrim
    1.09
     disqual
    1.00
     improper
    1.00
     Prosecutors
    0.98
     allegations
    0.96
     allege
    0.95
     felony
    0.95
    Activations Density 0.731%

    No Known Activations