© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1485
    Prev
    Next
    INDEX
    Explanations

    information related to countries, economies, and global statistics

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data related to global metrics and statistics

    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
    odox
    -0.71
    actionDate
    -0.71
    æĦ
    -0.70
    artifacts
    -0.66
     Cosponsors
    -0.66
    ĪĴ
    -0.64
    multiple
    -0.64
    assetsadobe
    -0.63
     Lover
    -0.61
    particularly
    -0.61
    POSITIVE LOGITS
     total
    1.19
     population
    1.16
     GDP
    1.12
     workforce
    1.08
     gross
    0.96
     polled
    0.93
     surveyed
    0.93
    total
    0.92
     Gross
    0.90
     electorate
    0.88
    Activations Density 0.162%

    No Known Activations