© 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. 10978
    Prev
    Next
    INDEX
    Explanations

    legal and criminal terms, particularly relating to different types of charges such as misdemeanor and felony

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal offenses and charges

    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
    obyl
    -0.89
    adle
    -0.87
    ator
    -0.83
    bits
    -0.82
    atives
    -0.81
    abeth
    -0.81
    atorial
    -0.80
    ators
    -0.79
    da
    -0.79
    rift
    -0.78
    POSITIVE LOGITS
     punishable
    1.28
     charges
    1.06
     probation
    1.03
     offenses
    1.03
     convictions
    0.97
     misdemeanor
    0.97
     arrests
    0.95
     perjury
    0.94
     burglary
    0.94
     arrest
    0.93
    Activations Density 0.040%

    No Known Activations