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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 10001
    Prev
    Next
    INDEX
    Explanations

    mentions of specific events or actions related to individuals assuming or leaving political office

    oai_token-act-pair · gpt-3.5-turbo

    references to political office and transitions between administrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ļéĨĴ
    -0.73
     Burnett
    -0.62
     acoustic
    -0.61
     Collider
    -0.60
     Drop
    -0.60
     Mutual
    -0.58
     hay
    -0.58
     interoper
    -0.58
     Ghosts
    -0.57
     Airl
    -0.57
    POSITIVE LOGITS
     presidency
    1.61
     govern
    1.48
     Presidency
    1.48
     elected
    1.47
    elected
    1.37
     administrations
    1.35
     administration
    1.26
     Cabinet
    1.23
     appointed
    1.22
     office
    1.22
    Activations Density 1.149%

    No Known Activations