Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 23237
    Prev
    Next
    INDEX
    Explanations

    mentions of missile tests and nuclear activities related to North Korea

    oai_token-act-pair · gpt-3.5-turbo

    references to missile and nuclear tests conducted by North Korea

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

    No Comments

    Negative Logits
     Homeless
    -0.81
     Corpse
    -0.75
    Ward
    -0.75
     Employees
    -0.74
     Barber
    -0.74
     Sacrament
    -0.73
    Effect
    -0.72
    rette
    -0.71
    Sym
    -0.71
     Bernard
    -0.71
    POSITIVE LOGITS
     submarine
    1.07
     missile
    1.04
     submarines
    1.00
     missiles
    0.96
     warheads
    0.93
     nuclear
    0.91
     destroyer
    0.91
     capabilities
    0.88
    ongyang
    0.87
     warships
    0.86
    Activations Density 0.213%

    No Known Activations