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

    Neuronpedia

    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. 4-RES-JB
    11. 19850
    Prev
    Next
    INDEX
    Explanations

    institutions or organizations with the word "Agency" in their name

    oai_token-act-pair · gpt-3.5-turbo

    references to various agencies related to research, government, or international organizations

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

    No Comments

    Negative Logits
    jiang
    -0.73
    aunder
    -0.72
    sticks
    -0.71
    erous
    -0.71
    lass
    -0.70
    bred
    -0.69
    stad
    -0.69
    isers
    -0.69
    lasses
    -0.68
    bring
    -0.67
    POSITIVE LOGITS
     Agency
    0.95
    ENCY
    0.80
    UTH
    0.77
     Authority
    0.74
    encies
    0.72
     Administrator
    0.71
     Coord
    0.71
    ption
    0.70
    uthor
    0.70
     Employees
    0.70
    Activations Density 0.014%

    No Known Activations