© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 489
    Prev
    Next
    INDEX
    Explanations

    the term "unemployment" within the text

    oai_token-act-pair · gpt-4-turbo

    words related to economic topics, especially focusing on unemployment

    oai_token-act-pair · gpt-3.5-turbo

    references to unemployment statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gran
    -0.79
    Interstitial
    -0.75
    ILE
    -0.71
    wig
    -0.68
    ebook
    -0.66
    kef
    -0.66
    agra
    -0.66
    ×Ļ×
    -0.65
    20439
    -0.65
    ¯¯¯¯¯¯¯¯
    -0.65
    POSITIVE LOGITS
     Unemployment
    1.10
     unemployment
    1.08
     unemploy
    0.94
    employment
    0.87
     unemployed
    0.81
    uates
    0.77
     contag
    0.76
    ©¶æ¥µ
    0.76
    uating
    0.72
    yip
    0.72
    Activations Density 0.009%

    No Known Activations