© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 5113
    Prev
    Next
    INDEX
    Explanations

    references to political news and events

    oai_token-act-pair · gpt-3.5-turbo

    references to significant political events or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skelet
    -0.70
     Gors
    -0.68
    DragonMagazine
    -0.67
     UNCLASSIFIED
    -0.65
    âĹ¼
    -0.64
     <[
    -0.64
    ynthesis
    -0.64
     %%
    -0.61
     Azerb
    -0.61
    emale
    -0.61
    POSITIVE LOGITS
     presumptive
    0.78
     Donald
    0.78
     embattled
    0.78
     lawmakers
    0.76
    WASHINGTON
    0.75
     GOP
    0.71
     Tuesday
    0.70
     frontman
    0.69
     Wednesday
    0.68
     Hillary
    0.68
    Activations Density 1.455%

    No Known Activations