© 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. 8-RES-JB
    11. 4626
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures with a title of "Vice President"

    oai_token-act-pair · gpt-3.5-turbo

    references to vice presidents

    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
    odi
    -0.85
    onite
    -0.80
    itsch
    -0.78
    yth
    -0.78
    ramid
    -0.76
     ding
    -0.73
    rical
    -0.71
    atable
    -0.67
    ologies
    -0.66
    rawdownloadcloneembedreportprint
    -0.66
    POSITIVE LOGITS
     versa
    1.12
     PRESIDENT
    0.91
     Princ
    0.85
     Vice
    0.83
     Presidents
    0.82
     Presidential
    0.80
     Grip
    0.79
    Vice
    0.79
     Admiral
    0.78
     President
    0.78
    Activations Density 0.009%

    No Known Activations