© 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. 4-RES-JB
    6. 9465
    Prev
    Next
    INDEX
    Explanations

    financial terms, names of financial institutions, and activities related to finance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial institutions and services

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

    No Comments

    Negative Logits
    lain
    -0.89
    poke
    -0.84
    qqa
    -0.75
    xon
    -0.74
    icular
    -0.74
    gom
    -0.73
    JV
    -0.72
    lr
    -0.72
    realDonaldTrump
    -0.71
    alin
    -0.69
    POSITIVE LOGITS
     Advis
    0.80
     Cards
    0.80
     Advisor
    0.79
     Services
    0.79
     Financial
    0.78
     Situation
    0.78
     Intelligence
    0.77
     Institution
    0.75
     Analyst
    0.73
     Transaction
    0.71
    Activations Density 0.011%

    No Known Activations