© 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. 8-RES-JB
    11. 6259
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Mitt Romney"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Mitt Romney."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ende
    -0.79
    theless
    -0.78
    netflix
    -0.73
     rul
    -0.72
    ĨĴ
    -0.72
    */(
    -0.71
    SHIP
    -0.70
     cryst
    -0.67
     DRAG
    -0.66
     livest
    -0.66
    POSITIVE LOGITS
     Romney
    1.50
    Romney
    1.15
     Mitt
    1.00
    sburgh
    0.85
     Hussein
    0.83
    ens
    0.82
     Santorum
    0.81
    enthal
    0.80
    erer
    0.79
     Anderson
    0.79
    Activations Density 0.017%

    No Known Activations