© 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. 1-RES-JB
    11. 3940
    Prev
    Next
    INDEX
    Explanations

    words related to business or investment portfolios

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of portfolios, particularly financial ones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ths
    -0.65
    ×Ļ
    -0.63
    ãģ¦
    -0.62
     Jude
    -0.62
    lling
    -0.62
    immer
    -0.61
     NOTICE
    -0.61
     Heart
    -0.61
    bians
    -0.60
    OUT
    -0.60
    POSITIVE LOGITS
     portfolio
    1.59
     portfolios
    1.56
    folio
    1.25
    folios
    1.24
     holdings
    0.92
    oleon
    0.83
     assignments
    0.80
    aird
    0.78
    ographies
    0.73
    olicy
    0.73
    Activations Density 0.005%

    No Known Activations