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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 16833
    Prev
    Next
    INDEX
    Explanations

    phrases related to US government institutions and political processes

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States and its political structure, particularly focusing on government entities and officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hots
    -0.74
    quickShipAvailable
    -0.71
     nick
    -0.69
    zbollah
    -0.69
     dod
    -0.65
    mobi
    -0.62
     racks
    -0.62
     livest
    -0.62
    esters
    -0.61
     [|
    -0.61
    POSITIVE LOGITS
     Constitution
    1.04
     Citizenship
    0.96
     Attorney
    0.81
     Affairs
    0.80
     Accountability
    0.79
     Postal
    0.78
     Federation
    0.76
     Treasury
    0.76
     Constitutional
    0.76
     Sovere
    0.75
    Activations Density 0.194%

    No Known Activations