© 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. 11-RES-JB
    11. 9081
    Prev
    Next
    INDEX
    Explanations

    financial terms and economic indicators

    oai_token-act-pair · gpt-3.5-turbo

    financial and economic metrics, particularly those related to credit, tax, and GDP percentages

    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
     replay
    -0.78
     summoning
    -0.75
     reinforcements
    -0.71
    AFTA
    -0.70
     droid
    -0.69
     overload
    -0.69
     cloning
    -0.67
     tomorrow
    -0.67
     loft
    -0.67
     prototypes
    -0.67
    POSITIVE LOGITS
     Percent
    1.56
     Percentage
    1.55
     (%)
    1.37
    Percent
    1.35
     Median
    1.29
     Population
    1.28
     %
    1.26
     (%
    1.25
     Unemployment
    1.23
     Females
    1.19
    Activations Density 0.251%

    No Known Activations