© 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. 11-RES-JB
    11. 9864
    Prev
    Next
    INDEX
    Explanations

    specific text indicating advertisements

    oai_token-act-pair · gpt-3.5-turbo

    the presence of advertisements or references to advertisements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     determination
    -0.61
    ĪĴ
    -0.61
    alist
    -0.57
     statistical
    -0.55
     awakening
    -0.53
     measurement
    -0.52
     tal
    -0.52
     accommodation
    -0.52
     deduct
    -0.51
     representative
    -0.51
    POSITIVE LOGITS
    advertisement
    0.77
     Continue
    0.74
    embed
    0.67
     CONTIN
    0.66
    RELATED
    0.62
     Cancel
    0.62
    é¾įå
    0.61
     VIDEOS
    0.61
     Expand
    0.61
     Advertisement
    0.59
    Activations Density 0.029%

    No Known Activations