© 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. 697
    Prev
    Next
    INDEX
    Explanations

    terms related to legal plea deals

    oai_token-act-pair · gpt-3.5-turbo

    references to legal plea agreements and negotiations

    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
    poll
    -0.75
     Kers
    -0.74
    lav
    -0.73
    ONES
    -0.73
    orians
    -0.72
     Frankfurt
    -0.67
    twitter
    -0.64
    idays
    -0.63
    ians
    -0.63
    aughters
    -0.62
    POSITIVE LOGITS
     plea
    1.10
     bargain
    1.10
     plead
    1.04
     barg
    1.00
     pled
    0.97
     pleading
    0.91
     bargaining
    0.85
     indictment
    0.85
     sentencing
    0.83
     pleas
    0.80
    Activations Density 0.006%

    No Known Activations