© 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. 10-RES-JB
    11. 2875
    Prev
    Next
    INDEX
    Explanations

    phrases related to nuclear conflict and military tensions

    oai_token-act-pair · gpt-3.5-turbo

    keywords associated with nuclear conflict and geopolitical tensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WRITE
    -0.73
     Volunte
    -0.72
     Parables
    -0.71
     Prest
    -0.71
     mould
    -0.69
     BMC
    -0.68
     Luck
    -0.68
     Gupta
    -0.68
    ogyn
    -0.68
    Luck
    -0.67
    POSITIVE LOGITS
     retali
    1.46
     retaliation
    1.37
     preempt
    1.36
     retaliate
    1.32
     escalation
    1.28
    uclear
    1.27
     airstrikes
    1.27
     aggression
    1.19
     warfare
    1.18
     unilateral
    1.17
    Activations Density 0.515%

    No Known Activations