© 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. 11-RES-JB
    11. 7489
    Prev
    Next
    INDEX
    Explanations

    mentions of shortages, especially related to housing and workforce

    oai_token-act-pair · gpt-3.5-turbo

    mentions of shortages in various contexts

    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
    agonist
    -0.83
    summary
    -0.78
    boxing
    -0.74
    Mania
    -0.72
    Heart
    -0.72
    ¬
    -0.71
    iquette
    -0.70
    ername
    -0.70
    hid
    -0.70
    eks
    -0.69
    POSITIVE LOGITS
     suitable
    1.31
     manpower
    1.22
     resources
    1.21
     replacements
    1.20
     talent
    1.16
     beds
    1.14
     spare
    1.14
     skilled
    1.14
     affordable
    1.14
     reliable
    1.13
    Activations Density 0.271%

    No Known Activations