© 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. 11-RES-JB
    11. 20534
    Prev
    Next
    INDEX
    Explanations

    words related to political events and figures, especially around statements or decisions

    oai_token-act-pair · gpt-3.5-turbo

    references to political events and emergency declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endum
    -0.71
    pmwiki
    -0.68
     afore
    -0.66
     ðŁĻĤ
    -0.65
    -.
    -0.64
     subsequ
    -0.64
     largeDownload
    -0.62
    âĢ¦âĢ¦
    -0.62
     perm
    -0.60
    âĢ¦âĢ¦âĢ¦âĢ¦
    -0.60
    POSITIVE LOGITS
     Kavanaugh
    0.88
     MORE
    0.81
     Dems
    0.77
     Biden
    0.66
    UFF
    0.64
     }}
    0.63
     Flake
    0.62
     Heller
    0.62
    ACTION
    0.62
     Election
    0.61
    Activations Density 0.048%

    No Known Activations