Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 8418
    Prev
    Next
    INDEX
    Explanations

    references to individuals related to the 2016 U.S. Presidential election involving Trump Jr., Manafort, and Kushner colluding with Russians

    oai_token-act-pair · gpt-3.5-turbo

    references to Donald Trump Jr. in relation to political events or controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     relegation
    -0.81
    ahime
    -0.80
     WCS
    -0.78
     Krug
    -0.78
     Samurai
    -0.78
     Bruins
    -0.77
     Fuk
    -0.77
     Worcester
    -0.77
     Pyr
    -0.76
     Canterbury
    -0.75
    POSITIVE LOGITS
    ossier
    1.31
     dossier
    1.13
    afort
    1.10
     subpoen
    0.99
     disclosures
    0.98
     revelations
    0.97
     allegations
    0.96
    ileaks
    0.96
    Leaks
    0.94
     leaks
    0.93
    Activations Density 0.174%

    No Known Activations