© 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 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. 0-RES-JB
    11. 2016
    Prev
    Next
    INDEX
    Explanations

    words related to political topics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Politics" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imeter
    -0.74
     input
    -0.70
     skilled
    -0.70
    ETF
    -0.66
     alpha
    -0.64
     fir
    -0.64
    FIG
    -0.64
    ault
    -0.64
     initial
    -0.64
    sel
    -0.63
    POSITIVE LOGITS
     Politics
    3.94
    Politics
    2.84
    politics
    2.30
     politics
    2.21
     POLIT
    1.86
     Political
    1.82
    Political
    1.76
    Polit
    1.65
     Elections
    1.50
    olitics
    1.49
    Activations Density 0.019%

    No Known Activations