© 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. 7592
    Prev
    Next
    INDEX
    Explanations

    references to financial indices like the S&P 500

    oai_token-act-pair · gpt-3.5-turbo

    references to the S&P 500 stock index and financial metrics associated with it

    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
    wic
    -0.87
    netflix
    -0.83
    requ
    -0.81
     indoctr
    -0.75
     infiltr
    -0.72
    nesia
    -0.72
    ̶
    -0.71
     smugglers
    -0.71
    spawn
    -0.69
    scenes
    -0.69
    POSITIVE LOGITS
     Investors
    1.02
     Dow
    0.92
    daq
    0.90
     Rating
    0.87
     index
    0.87
     Index
    0.86
     Composite
    0.85
     indices
    0.84
     rating
    0.81
     Investor
    0.81
    Activations Density 0.120%

    No Known Activations