© 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. 18631
    Prev
    Next
    INDEX
    Explanations

    political keywords and terms

    oai_token-act-pair · gpt-3.5-turbo

    references to political events and controversies

    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
    ustomed
    -0.87
    imental
    -0.81
     orn
    -0.78
    earchers
    -0.77
    vity
    -0.74
    isure
    -0.74
    eger
    -0.73
     accustomed
    -0.72
     inscribed
    -0.72
     solitude
    -0.71
    POSITIVE LOGITS
     Wikileaks
    1.59
     TRUMP
    1.51
     DNC
    1.47
     HRC
    1.47
     Benghazi
    1.46
    Hillary
    1.40
     Putin
    1.39
     Hillary
    1.39
    TRUMP
    1.39
     Dems
    1.38
    Activations Density 1.125%

    No Known Activations