Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 15872
    Prev
    Next
    INDEX
    Explanations

    economic indicators and financial terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic indicators and construction activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Milo
    -0.70
    aroo
    -0.69
    cific
    -0.68
    agle
    -0.66
    obos
    -0.66
     gag
    -0.64
     pedoph
    -0.63
     Canaver
    -0.63
     LAPD
    -0.63
    ulhu
    -0.62
    POSITIVE LOGITS
     sector
    0.97
     accounted
    0.89
    sector
    0.88
     Sector
    0.81
     economist
    0.80
     (%
    0.80
     sectors
    0.80
     households
    0.77
     Consumption
    0.77
     unemployment
    0.76
    Activations Density 0.572%

    No Known Activations