© 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
    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. 7051
    Prev
    Next
    INDEX
    Explanations

    the word "trademark" or variations of it in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to trademarks and related legal terms

    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
     Aux
    -0.74
    ECD
    -0.71
     Isles
    -0.69
    agan
    -0.69
    apter
    -0.69
     Methodist
    -0.62
     Rae
    -0.61
     Presence
    -0.59
     Utilities
    -0.59
    OTT
    -0.59
    POSITIVE LOGITS
     trademarks
    1.06
    emark
    1.05
     trademark
    0.95
    eers
    0.93
     infringement
    0.90
    eer
    0.90
     registrations
    0.85
    itionally
    0.83
     Seym
    0.80
    ively
    0.79
    Activations Density 0.011%

    No Known Activations