© 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. 16060
    Prev
    Next
    INDEX
    Explanations

    phrases related to infringement on intellectual property or legal rights

    oai_token-act-pair · gpt-3.5-turbo

    terms related to patent infringement and legal violations

    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
    ilts
    -0.79
    ãĤ©
    -0.71
    ionic
    -0.66
    ellen
    -0.63
    hall
    -0.62
    adi
    -0.62
     Runner
    -0.62
    hap
    -0.61
    çĭ
    -0.60
    SO
    -0.59
    POSITIVE LOGITS
     infring
    0.99
    ements
    0.96
     infringement
    0.89
     upon
    0.88
    yrights
    0.86
     infringing
    0.78
    eding
    0.76
    urious
    0.72
    ulent
    0.72
     trespass
    0.71
    Activations Density 0.043%

    No Known Activations