© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 9760
    Prev
    Next
    INDEX
    Explanations

    phrases related to infringement, especially in the context of patents and intellectual property

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal infringement, particularly concerning patents and intellectual property

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilts
    -0.87
    roth
    -0.74
    agan
    -0.73
    adi
    -0.71
    =-=-=-=-=-=-=-=-
    -0.66
    hall
    -0.64
    night
    -0.63
    lain
    -0.62
    nexus
    -0.62
    bern
    -0.61
    POSITIVE LOGITS
     infring
    1.35
     infringement
    1.21
     infringing
    1.12
    yrights
    0.77
    ãĤº
    0.74
    rodu
    0.72
     proble
    0.70
     inhibition
    0.70
     copyrighted
    0.68
     poaching
    0.68
    Activations Density 0.010%

    No Known Activations