© 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. 14334
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal charges and legal consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to facing legal charges or potential sentences

    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
     Telesc
    -0.78
    æ©Ł
    -0.76
    æĦ
    -0.75
    unny
    -0.74
    iom
    -0.74
    icator
    -0.71
    tel
    -0.71
    iverse
    -0.71
    isive
    -0.70
    oeuv
    -0.68
    POSITIVE LOGITS
     charges
    1.38
     felony
    1.21
     prosecution
    1.14
     manslaughter
    1.13
     extradition
    1.11
     misdemeanor
    1.07
     sentencing
    1.05
     criminal
    1.03
     jail
    1.02
     deportation
    1.01
    Activations Density 0.085%

    No Known Activations