© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 6622
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to politics, leadership, and events

    oai_token-act-pair · gpt-3.5-turbo

    words associated with political events and leadership transitions

    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
    oppers
    -0.74
    riks
    -0.70
    è¦ļéĨĴ
    -0.68
     Wonderland
    -0.67
    Balt
    -0.67
    áµ
    -0.67
     scouts
    -0.66
     Exclusive
    -0.65
    eks
    -0.64
     broch
    -0.64
    POSITIVE LOGITS
     assassinated
    1.78
     died
    1.51
     resign
    1.50
     retire
    1.43
     resigned
    1.39
     murdered
    1.38
     deceased
    1.37
     retiring
    1.37
     killed
    1.34
     resignation
    1.33
    Activations Density 0.837%

    No Known Activations