© 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. 16185
    Prev
    Next
    INDEX
    Explanations

    words related to political affairs and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to political consequences and actions surrounding leadership

    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
     haha
    -0.89
    xual
    -0.86
    Kids
    -0.70
     Vs
    -0.69
     lol
    -0.66
    sexual
    -0.66
     :)
    -0.65
     XY
    -0.64
     individuality
    -0.64
     referrals
    -0.64
    POSITIVE LOGITS
     neocons
    1.03
     Kissinger
    0.92
     embold
    0.90
     rhetorical
    0.90
     Bannon
    0.88
    Putin
    0.87
     sober
    0.87
     Hollande
    0.87
     McConnell
    0.86
     Republicans
    0.86
    Activations Density 0.990%

    No Known Activations