© 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. 9-RES-JB
    11. 11281
    Prev
    Next
    INDEX
    Explanations

    legal terms and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to serious crimes and violent offenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enlarge
    -0.71
    DragonMagazine
    -0.70
    hower
    -0.67
     Keynes
    -0.66
    Quote
    -0.64
     attrition
    -0.63
    ulously
    -0.62
     theirs
    -0.62
     trillions
    -0.62
    kefeller
    -0.61
    POSITIVE LOGITS
     unlawful
    1.00
     unlawfully
    0.97
     firearm
    0.91
     felon
    0.90
    angering
    0.88
     lawful
    0.88
     felony
    0.85
     intoxicated
    0.84
     juveniles
    0.83
     minors
    0.83
    Activations Density 0.290%

    No Known Activations