© 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. 10-RES-JB
    11. 2996
    Prev
    Next
    INDEX
    Explanations

    phrases related to economics and global statistics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FactoryReloaded
    -0.75
    CVE
    -0.74
    tones
    -0.69
    bol
    -0.66
    umenthal
    -0.66
    Ô
    -0.66
    zy
    -0.66
    notations
    -0.65
     Misty
    -0.65
    ochet
    -0.64
    POSITIVE LOGITS
     GDP
    1.52
     economy
    1.43
     households
    1.23
     economies
    1.21
     population
    1.19
     workforce
    1.16
     incomes
    1.12
     unemployment
    1.11
     income
    1.07
     median
    1.05
    Activations Density 0.230%

    No Known Activations