© 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. 11-RES-JB
    11. 7472
    Prev
    Next
    INDEX
    Explanations

    government-related entities and actions, such as councils, legislatures, and votes

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental bodies and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fountain
    -0.70
     IMAGES
    -0.69
     informants
    -0.65
     Bian
    -0.65
     Ange
    -0.64
     sleeper
    -0.63
    itbart
    -0.63
     Horus
    -0.63
     attribution
    -0.62
     competitor
    -0.62
    POSITIVE LOGITS
     voted
    1.51
     passed
    1.46
     unanimously
    1.43
     approved
    1.38
     overwhelmingly
    1.26
     repealed
    1.24
     enacted
    1.20
     adjourn
    1.18
     debated
    1.16
     ratified
    1.16
    Activations Density 0.205%

    No Known Activations