© 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. 12498
    Prev
    Next
    INDEX
    Explanations

    words related to criminal offenses, especially felony charges

    oai_token-act-pair · gpt-3.5-turbo

    references to felony charges

    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
    atorial
    -0.88
    ator
    -0.85
    adle
    -0.85
    obyl
    -0.84
    ators
    -0.83
    este
    -0.82
    choes
    -0.82
    ates
    -0.81
    abeth
    -0.80
    inki
    -0.79
    POSITIVE LOGITS
     punishable
    1.21
     offenses
    1.06
     probation
    1.04
     convictions
    1.02
     DUI
    1.01
     arrest
    0.99
     misdemeanor
    0.99
     conviction
    0.97
     felony
    0.97
     charges
    0.96
    Activations Density 0.040%

    No Known Activations