© 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. 2-RES-JB
    11. 436
    Prev
    Next
    INDEX
    Explanations

    the term "party" within a political context

    oai_token-act-pair · gpt-4-turbo

    terms related to political parties, their actions, and dynamics

    oai_token-act-pair · gpt-3.5-turbo

    references to a political party and its dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onday
    -0.71
    angelo
    -0.71
    alam
    -0.69
     Marketable
    -0.69
     DOI
    -0.68
     Tile
    -0.64
    chie
    -0.63
    iries
    -0.63
     Wheat
    -0.62
    ravings
    -0.61
    POSITIVE LOGITS
    goers
    1.00
     insiders
    0.94
     affiliation
    0.87
     faithful
    0.86
     establishment
    0.85
    agogue
    0.83
     parties
    0.79
    isphere
    0.79
     party
    0.78
    eering
    0.77
    Activations Density 0.035%

    No Known Activations