© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 2764
    Prev
    Next
    INDEX
    Explanations

    phrases related to support, assistance, and resilience

    oai_token-act-pair · gpt-3.5-turbo

    expressions of support and encouragement during difficult times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dems
    -0.74
     libertarians
    -0.70
     liberals
    -0.69
     Democrats
    -0.66
     disclaimer
    -0.64
     economists
    -0.64
     Schumer
    -0.64
     pity
    -0.63
     Mexicans
    -0.60
     socialists
    -0.60
    POSITIVE LOGITS
     challenging
    1.17
     difficult
    1.16
     challenges
    1.04
     perilous
    1.04
     turbulent
    1.04
     uncertain
    1.02
     situations
    1.00
     stressful
    0.99
     evolving
    0.97
     crises
    0.95
    Activations Density 0.422%

    No Known Activations