© 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. 11-RES-JB
    11. 9960
    Prev
    Next
    INDEX
    Explanations

    mentions of humanitarian aid and aid organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to humanitarian aid and organizations involved in aid efforts

    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
    beard
    -0.74
    ross
    -0.69
    steamapps
    -0.69
     Shad
    -0.68
     Beard
    -0.67
     fry
    -0.66
     Detective
    -0.66
    ille
    -0.65
    nen
    -0.63
     Barkley
    -0.63
    POSITIVE LOGITS
     packages
    1.10
     agencies
    0.96
     recipients
    0.94
     package
    0.93
    giving
    0.91
     aid
    0.91
     shipments
    0.90
     supplies
    0.87
     deliveries
    0.87
     seekers
    0.86
    Activations Density 0.082%

    No Known Activations