© 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. 10761
    Prev
    Next
    INDEX
    Explanations

    phrases related to political interference and investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to Russian interference in U.S. elections

    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
    Label
    -0.74
    BIL
    -0.71
    arcer
    -0.71
     landlords
    -0.66
     [+
    -0.65
     glim
    -0.65
    ilial
    -0.64
    eteria
    -0.64
     Correctional
    -0.64
     hect
    -0.63
    POSITIVE LOGITS
     election
    1.20
     DNC
    1.12
     TRUMP
    1.11
     elections
    1.10
     Trump
    1.03
    election
    1.02
     Election
    0.99
     presidential
    0.99
     electing
    0.99
     Ukraine
    0.98
    Activations Density 0.169%

    No Known Activations