© 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. 7-RES-JB
    11. 22901
    Prev
    Next
    INDEX
    Explanations

    phrases related to political roles and affiliations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating roles or positions of advisors or aides in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     glances
    -0.68
     deductions
    -0.66
    rings
    -0.65
     sockets
    -0.63
    rawdownloadcloneembedreportprint
    -0.62
    need
    -0.61
     bundles
    -0.61
     pauses
    -0.61
    rences
    -0.60
    rio
    -0.59
    POSITIVE LOGITS
     testify
    0.76
     inform
    0.76
     ensure
    0.74
     whom
    0.74
     oversee
    0.73
     accompany
    0.73
     Misc
    0.73
    wered
    0.72
     protect
    0.72
     appease
    0.71
    Activations Density 0.095%

    No Known Activations