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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 19915
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of vetoing

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of veto power and its applications in governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TM
    -0.67
    Fi
    -0.66
     laid
    -0.63
    FORM
    -0.63
    started
    -0.60
     Gaw
    -0.60
     Fit
    -0.60
    elf
    -0.60
    Mag
    -0.58
     Ther
    -0.58
    POSITIVE LOGITS
     veto
    4.64
     vetoed
    2.79
     filibuster
    1.38
     override
    1.20
     boycott
    1.05
     bluff
    1.01
     boycot
    1.00
     pardon
    0.99
     Voting
    0.99
     filib
    0.98
    Activations Density 0.018%

    No Known Activations