© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 2733
    Prev
    Next
    INDEX
    Explanations

    politically related terms, especially those associated with political parties and figures

    oai_token-act-pair · gpt-3.5-turbo

    references to political parties and their candidates or affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "$:/
    -0.82
    phasis
    -0.80
    imaru
    -0.75
    cellent
    -0.74
    peak
    -0.73
    rompt
    -0.72
    ailable
    -0.71
    ramid
    -0.71
    artment
    -0.71
    catentry
    -0.70
    POSITIVE LOGITS
     filmmaker
    1.12
     entrepreneur
    1.12
     strategist
    1.12
     newcomer
    1.11
     guru
    1.10
     comedian
    1.09
     thinker
    1.08
     billionaire
    1.07
     architect
    1.07
     superstar
    1.07
    Activations Density 0.351%

    No Known Activations