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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 13474
    Prev
    Next
    INDEX
    Explanations

    information related to political news and events concerning North Korea and its missile activities

    oai_token-act-pair · gpt-3.5-turbo

    references to missile tests and related military actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cullen
    -0.83
     Equality
    -0.82
     Homeless
    -0.78
     Anthropology
    -0.76
     Adult
    -0.74
    College
    -0.74
     Equity
    -0.74
     "$:/
    -0.73
     Wage
    -0.73
     Calvin
    -0.73
    POSITIVE LOGITS
     missiles
    1.53
     missile
    1.52
     warheads
    1.50
     deton
    1.29
     unmanned
    1.27
     Missile
    1.27
     submarines
    1.24
     ballistic
    1.22
     reconnaissance
    1.22
     rockets
    1.22
    Activations Density 0.590%

    No Known Activations