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

    Neuronpedia

    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. 8-RES-JB
    11. 1356
    Prev
    Next
    INDEX
    Explanations

    phrases related to shortages in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shortage" and its variations related to insufficient supply or availability of various resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    robe
    -0.79
    tip
    -0.74
    der
    -0.71
    ramid
    -0.68
    orse
    -0.67
    wig
    -0.65
    atom
    -0.64
    oral
    -0.64
    lynn
    -0.62
    issance
    -0.62
    POSITIVE LOGITS
     shortages
    0.96
     manpower
    0.89
     supply
    0.83
     quotas
    0.82
     surplus
    0.81
     shortage
    0.81
     liquidity
    0.79
     quantity
    0.77
     glut
    0.77
     quantities
    0.75
    Activations Density 0.098%

    No Known Activations