© 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. 19680
    Prev
    Next
    INDEX
    Explanations

    mentions of government-related entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to government-related topics and policies

    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
    CONT
    -0.78
     Tome
    -0.74
    sbm
    -0.73
    ussen
    -0.72
    bring
    -0.72
    omas
    -0.69
    vae
    -0.68
    tom
    -0.67
     Spiel
    -0.67
    lihood
    -0.67
    POSITIVE LOGITS
     bureaucracy
    1.06
     agencies
    1.03
     government
    0.97
     agency
    0.96
     administration
    0.92
    arily
    0.90
     officials
    0.89
     shutdown
    0.87
     mandated
    0.87
     administrator
    0.87
    Activations Density 0.064%

    No Known Activations