Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 10180
    Prev
    Next
    INDEX
    Explanations

    mentions of legal proceedings, specifically related to pleas and bargains

    oai_token-act-pair · gpt-3.5-turbo

    references to legal plea agreements or bargains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONES
    -0.73
    orians
    -0.72
    idays
    -0.71
    aughters
    -0.71
    lav
    -0.68
    7601
    -0.67
    ians
    -0.67
    icky
    -0.65
    orrect
    -0.65
     Kers
    -0.65
    POSITIVE LOGITS
     plea
    1.08
     bargain
    1.04
     plead
    0.99
     barg
    0.96
     pled
    0.93
     pleading
    0.87
     bargaining
    0.79
     Ramsey
    0.79
     sentencing
    0.78
     parole
    0.77
    Activations Density 0.011%

    No Known Activations