© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 15073
    Prev
    Next
    INDEX
    Explanations

    terms related to military relationships, especially focusing on comradeship and loyalty

    oai_token-act-pair · gpt-3.5-turbo

    references to comrades or companionship

    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
    okin
    -0.87
    Lew
    -0.72
     fertility
    -0.71
    title
    -0.68
    oen
    -0.62
    urred
    -0.61
    ALE
    -0.59
    other
    -0.58
    Ven
    -0.58
    UD
    -0.58
    POSITIVE LOGITS
     comrade
    1.28
     comrades
    1.13
    nect
    0.92
    chwitz
    0.90
    mates
    0.87
    hip
    0.86
     buddies
    0.79
     congr
    0.75
    ĸļ
    0.74
    members
    0.74
    Activations Density 0.005%

    No Known Activations