© 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. 427
    Prev
    Next
    INDEX
    Explanations

    emerging trends, technologies, and economies

    oai_token-act-pair · gpt-3.5-turbo

    references to emerging markets and technologies

    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
    fax
    -0.90
    bia
    -0.88
    tesy
    -0.83
    cise
    -0.76
    udging
    -0.75
    udeb
    -0.73
    zzi
    -0.72
    ded
    -0.72
    respective
    -0.70
    claimer
    -0.68
    POSITIVE LOGITS
     technologies
    1.03
     Opportun
    0.98
     economies
    0.95
     talent
    0.88
     talents
    0.86
     markets
    0.86
     prospects
    0.83
     trends
    0.82
     democracies
    0.79
     Markets
    0.78
    Activations Density 0.060%

    No Known Activations