© 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. 3-RES-JB
    11. 10740
    Prev
    Next
    INDEX
    Explanations

    references to the position of governor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to political leaders, especially governors

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opter
    -0.82
    origin
    -0.76
    Else
    -0.71
    ener
    -0.70
    uran
    -0.70
    itton
    -0.68
    crew
    -0.68
    ple
    -0.68
    rd
    -0.66
    dest
    -0.66
    POSITIVE LOGITS
     governor
    1.07
     Governor
    0.95
     Cuomo
    0.78
     governors
    0.78
     vetoed
    0.74
     antid
    0.73
    govern
    0.72
     Gov
    0.71
    esses
    0.71
     gubernatorial
    0.70
    Activations Density 0.009%

    No Known Activations