© 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. 0-RES-JB
    6. 20237
    Prev
    Next
    INDEX
    Explanations

    references to military armies

    oai_token-act-pair · gpt-3.5-turbo

    references to military forces or armies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ñ
    -0.71
     coinc
    -0.65
     Regulatory
    -0.64
     ®
    -0.64
     Topic
    -0.63
     Satoshi
    -0.63
    Seg
    -0.62
     Stam
    -0.62
    Block
    -0.62
     Referred
    -0.61
    POSITIVE LOGITS
     army
    3.53
     armies
    2.54
    Army
    2.40
     Army
    2.38
     navy
    1.81
     soldiers
    1.67
     infantry
    1.65
     troops
    1.64
     military
    1.61
     soldier
    1.54
    Activations Density 0.017%

    No Known Activations