© 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. 7064
    Prev
    Next
    INDEX
    Explanations

    phrases related to political parties, especially the Tea Party

    oai_token-act-pair · gpt-3.5-turbo

    references to the Tea Party and anti-choice movements

    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
     captcha
    -0.73
    iour
    -0.71
     concess
    -0.68
     RIP
    -0.67
    BILITIES
    -0.67
     Adjusted
    -0.67
     Kear
    -0.65
     Yi
    -0.65
    currently
    -0.64
    manager
    -0.64
    POSITIVE LOGITS
     extremists
    1.00
     pamph
    0.95
     orthodoxy
    0.94
     extremism
    0.92
     extremist
    0.92
    atism
    0.88
    ervative
    0.87
     tracts
    0.87
     adherents
    0.86
     conservatives
    0.86
    Activations Density 0.244%

    No Known Activations