© 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. 1-RES-JB
    11. 13138
    Prev
    Next
    INDEX
    Explanations

    names of high-ranking military and intelligence officials

    oai_token-act-pair · gpt-3.5-turbo

    mentions of key individuals related to U.S. intelligence and military leadership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tails
    -0.85
     Vag
    -0.68
    stay
    -0.68
    Seg
    -0.67
    estate
    -0.66
    ר
    -0.65
     Viking
    -0.64
    gra
    -0.64
    mix
    -0.64
    ¢
    -0.64
    POSITIVE LOGITS
     Clapper
    1.41
     Nunes
    0.89
     Brennan
    0.77
    ascus
    0.77
     Rasmussen
    0.76
     briefings
    0.76
    iets
    0.73
     Dempsey
    0.72
    cffff
    0.71
    asar
    0.70
    Activations Density 0.011%

    No Known Activations