© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 20227
    Prev
    Next
    INDEX
    Explanations

    phrases related to patent infringement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "infringe" and its variations, which are related to legal violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilde
    -0.73
    adi
    -0.69
    hall
    -0.64
     Belt
    -0.64
    brace
    -0.64
    ionic
    -0.63
    night
    -0.62
    ilts
    -0.61
    ruff
    -0.61
     unification
    -0.61
    POSITIVE LOGITS
     infringement
    1.00
     infring
    0.99
     infringing
    0.96
    yrights
    0.92
    yright
    0.81
    ements
    0.79
     upon
    0.77
     tresp
    0.71
     copyrighted
    0.70
     Intellectual
    0.70
    Activations Density 0.040%

    No Known Activations