© 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. 10-RES-JB
    11. 11478
    Prev
    Next
    INDEX
    Explanations

    references to specific political figures or figures related to politics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political figures, particularly during discussions of their actions and controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actionDate
    -0.74
    lehem
    -0.70
    DAQ
    -0.69
     Mandatory
    -0.65
    sembly
    -0.62
     Mehran
    -0.61
    !/
    -0.61
     Artemis
    -0.61
    ammy
    -0.61
    Redd
    -0.60
    POSITIVE LOGITS
     himself
    1.13
    's
    0.95
     aides
    0.93
     Himself
    0.88
     swore
    0.86
     spends
    0.85
     prefers
    0.84
     complains
    0.82
     believes
    0.80
     knows
    0.79
    Activations Density 0.225%

    No Known Activations