© 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. 1-RES-JB
    11. 24039
    Prev
    Next
    INDEX
    Explanations

    mentions of various state governors

    oai_token-act-pair · gpt-3.5-turbo

    mentions of governors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Artemis
    -0.72
    yrinth
    -0.64
    schild
    -0.63
     Shattered
    -0.63
    anwhile
    -0.63
     Rumble
    -0.62
     Warfare
    -0.62
     Primordial
    -0.61
     Horde
    -0.61
     Zeus
    -0.61
    POSITIVE LOGITS
     Gov
    1.16
    govern
    0.97
     Governor
    0.94
    Gov
    0.82
    Govern
    0.79
    iture
    0.76
     Legisl
    0.76
     Governors
    0.75
     governor
    0.74
    cipled
    0.74
    Activations Density 0.004%

    No Known Activations