© 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. 9-RES-JB
    11. 10151
    Prev
    Next
    INDEX
    Explanations

    specific mentions of governmental organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various organizations or government bureaus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IFE
    -0.70
    terday
    -0.67
     Vader
    -0.66
    isks
    -0.66
     wart
    -0.64
    orem
    -0.64
    Beg
    -0.62
    castle
    -0.59
     Loving
    -0.59
    ipedia
    -0.58
    POSITIVE LOGITS
    ureau
    1.08
    oreal
    0.96
    cr
    0.94
    udget
    0.77
     Bureau
    0.73
    omial
    0.70
    RET
    0.70
    ration
    0.70
    ular
    0.70
    oro
    0.70
    Activations Density 0.034%

    No Known Activations