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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 17802
    Prev
    Next
    INDEX
    Explanations

    terms related to legal procedures and penalties, particularly focusing on probation and restitution

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal supervision and sentencing, specifically probation

    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
    xxxxxxxx
    -0.67
    bern
    -0.63
    ynchron
    -0.62
    hedral
    -0.62
    Dust
    -0.62
    989
    -0.62
    rencies
    -0.61
    ched
    -0.61
    Americans
    -0.60
    ãĤ¨
    -0.59
    POSITIVE LOGITS
     probation
    1.28
     parole
    0.98
     confir
    0.95
     revocation
    0.83
    ally
    0.76
    urous
    0.76
    ary
    0.75
    etheless
    0.75
    onding
    0.71
    enforcement
    0.71
    Activations Density 0.013%

    No Known Activations