© 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. 6-RES-JB
    11. 17825
    Prev
    Next
    INDEX
    Explanations

    words related to closures and emergency situations

    oai_token-act-pair · gpt-3.5-turbo

    references to closures and evacuations due to emergencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plagiar
    -0.85
     genius
    -0.80
     narcissistic
    -0.78
     charisma
    -0.76
     Inher
    -0.76
     Invention
    -0.75
     immortal
    -0.74
     immortality
    -0.74
     someday
    -0.74
     autobi
    -0.73
    POSITIVE LOGITS
     evacuated
    1.20
     evacuation
    1.15
     evac
    1.06
     crews
    1.04
    bris
    0.99
     evacuate
    0.99
     ambul
    0.98
     closures
    0.95
     outage
    0.92
     emergency
    0.90
    Activations Density 1.076%

    No Known Activations