© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 657
    Prev
    Next
    INDEX
    Explanations

    crimes and legal charges

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to criminal charges and legal offenses

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

    No Comments

    Negative Logits
    DragonMagazine
    -1.02
    selves
    -0.88
     Ruins
    -0.79
    hower
    -0.78
    isSpecialOrderable
    -0.76
     Programme
    -0.74
    angular
    -0.74
     surprises
    -0.73
     ãĤµ
    -0.73
    ãĤ¿
    -0.72
    POSITIVE LOGITS
     felony
    1.54
     misdemeanor
    1.45
     manslaughter
    1.32
     felon
    1.29
     parole
    1.24
     sentencing
    1.23
     perjury
    1.20
     prosecution
    1.19
     wrongful
    1.17
     custody
    1.16
    Activations Density 1.073%

    No Known Activations