© 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. 6-RES-JB
    11. 11801
    Prev
    Next
    INDEX
    Explanations

    financial terms related to the Dow Jones Industrial Average

    oai_token-act-pair · gpt-3.5-turbo

    references to the Dow Jones Industrial Average and related financial terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é»Ĵ
    -0.71
     Prosecut
    -0.71
    REDACTED
    -0.69
     Reach
    -0.65
     Gutenberg
    -0.65
    ocene
    -0.63
     Kenyan
    -0.62
    ĸļ
    -0.61
     prosecut
    -0.61
    ictions
    -0.61
    POSITIVE LOGITS
    cake
    1.01
    lings
    0.94
    minster
    0.92
    rey
    0.84
    rie
    0.84
    ried
    0.84
     Dow
    0.84
    daq
    0.84
    isher
    0.83
    ener
    0.82
    Activations Density 0.015%

    No Known Activations