© 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. 10-RES-JB
    11. 13702
    Prev
    Next
    INDEX
    Explanations

    specific legal terms, particularly related to ordinances and acts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of ordinances and related legal or regulatory terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prus
    -0.82
    çīĪ
    -0.74
    女
    -0.68
    atform
    -0.67
    ycle
    -0.66
    orous
    -0.65
    pmwiki
    -0.65
    adeon
    -0.64
    kiss
    -0.64
    ingen
    -0.64
    POSITIVE LOGITS
    nance
    0.97
    inance
    0.93
    ered
    0.89
    inances
    0.85
    eal
    0.83
    inary
    0.79
    eering
    0.78
    vals
    0.74
    eals
    0.72
    wered
    0.70
    Activations Density 0.101%

    No Known Activations