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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 23694
    Prev
    Next
    INDEX
    Explanations

    terms related to financial brokerage

    oai_token-act-pair · gpt-3.5-turbo

    references to financial intermediaries involved in trading or investment activities

    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
    atche
    -0.72
     Extrem
    -0.72
    MN
    -0.70
    phas
    -0.69
    printed
    -0.68
     Orwell
    -0.66
     Bie
    -0.64
    liam
    -0.63
     Liberties
    -0.62
    teness
    -0.61
    POSITIVE LOGITS
     broker
    1.14
     brokerage
    0.97
     brokers
    0.94
     trader
    0.81
    rador
    0.80
    eers
    0.79
    selling
    0.78
    folios
    0.77
    deal
    0.74
     trading
    0.73
    Activations Density 0.010%

    No Known Activations