© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 11520
    Prev
    Next
    INDEX
    Explanations

    terms related to government departments, with a specific focus on the Treasury Department

    oai_token-act-pair · gpt-3.5-turbo

    references to the Treasury Department

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bring
    -0.80
     Fuk
    -0.73
    olulu
    -0.67
    bleacher
    -0.67
     Jenner
    -0.66
    indu
    -0.64
    MQ
    -0.63
    eston
    -0.63
    SOURCE
    -0.62
     Gamergate
    -0.62
    POSITIVE LOGITS
    asury
    1.19
     Treasury
    0.92
     Secretary
    0.91
     Institution
    0.82
     Department
    0.80
     treasury
    0.79
     securities
    0.79
     secretary
    0.78
     secretaries
    0.71
     coffers
    0.71
    Activations Density 0.006%

    No Known Activations