© 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. 3193
    Prev
    Next
    INDEX
    Explanations

    specific references to the actions and statements of the US President, particularly related to policy changes and political events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Trump" and related political references

    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
     confessions
    -0.84
     Sleeping
    -0.72
    atha
    -0.72
    lehem
    -0.68
    ITNESS
    -0.68
     Alic
    -0.68
     pts
    -0.67
    tics
    -0.66
     Leigh
    -0.66
     journalistic
    -0.65
    POSITIVE LOGITS
     mandated
    1.12
     enacted
    1.05
     legisl
    1.03
     mandate
    1.02
     Administration
    1.00
     repealed
    0.99
     mandates
    0.99
     approved
    0.96
     administration
    0.95
     vetoed
    0.95
    Activations Density 0.312%

    No Known Activations