© 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. 2-RES-JB
    6. 5527
    Prev
    Next
    INDEX
    Explanations

    instances of the word "troops" occurring in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to military troops

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Consumer
    -0.81
    lihood
    -0.79
    Ħ¢
    -0.75
    Cand
    -0.72
    MAL
    -0.71
    Liter
    -0.69
     Literary
    -0.68
    âĶģ
    -0.66
     Sloan
    -0.66
     Mercury
    -0.66
    POSITIVE LOGITS
     troops
    1.09
     stationed
    1.07
     garrison
    0.93
     fatig
    0.92
     troop
    0.92
    alions
    0.92
     commanders
    0.90
     soldiers
    0.90
     deployed
    0.86
     deployments
    0.84
    Activations Density 0.023%

    No Known Activations