© 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. 9-RES-JB
    11. 16049
    Prev
    Next
    INDEX
    Explanations

    words related to politics, government positions, and legal matters, potentially focusing on controversies or scandals

    oai_token-act-pair · gpt-3.5-turbo

    fragments containing references to individuals, places, and events

    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
     Amon
    -0.87
    attach
    -0.80
     arrang
    -0.79
    ATOR
    -0.77
    AT
    -0.74
    ACY
    -0.74
     Amp
    -0.73
    asin
    -0.72
     awa
    -0.71
    ammy
    -0.71
    POSITIVE LOGITS
    stein
    0.94
    tein
    0.91
    pedia
    0.86
    wyn
    0.84
    ria
    0.82
    rian
    0.81
    edia
    0.81
    ´
    0.80
    rington
    0.80
    ri
    0.79
    Activations Density 0.417%

    No Known Activations