© 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. 7216
    Prev
    Next
    INDEX
    Explanations

    references to political figures, particularly focusing on the name "Bolton" along with related words and names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly John Bolton and Patrick Buchanan

    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
    ĩ
    -0.90
    encer
    -0.87
    olan
    -0.78
    yll
    -0.78
    Depth
    -0.75
    ¨
    -0.73
    Ó
    -0.73
    į
    -0.73
    Aren
    -0.72
    imity
    -0.72
    POSITIVE LOGITS
     transplant
    0.71
     disembark
    0.68
     calibr
    0.68
     trump
    0.68
     antioxidants
    0.65
    ifestyle
    0.65
     conver
    0.65
    tsky
    0.63
    etheless
    0.63
    estone
    0.63
    Activations Density 0.029%

    No Known Activations