© 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. 2-RES-JB
    11. 17183
    Prev
    Next
    INDEX
    Explanations

    words related to governmental actions, specifically the use of veto power

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "veto" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arist
    -0.82
    Sea
    -0.76
    EAR
    -0.72
    adr
    -0.71
    ondo
    -0.70
    MO
    -0.70
    akers
    -0.69
     Gaia
    -0.68
     Emerging
    -0.68
    OST
    -0.68
    POSITIVE LOGITS
     veto
    1.43
     vetoed
    1.23
    zai
    0.92
     bluff
    0.92
     amnesty
    0.86
     sugg
    0.79
     override
    0.79
    utive
    0.74
     overr
    0.74
     deterrent
    0.73
    Activations Density 0.007%

    No Known Activations