© 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. 10-RES-JB
    11. 14004
    Prev
    Next
    INDEX
    Explanations

    words related to finance and the financial sector

    oai_token-act-pair · gpt-3.5-turbo

    references to the financial sector and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.86
    hered
    -0.77
    imately
    -0.76
    IRO
    -0.70
    ILE
    -0.70
    uve
    -0.68
    uph
    -0.68
    imus
    -0.67
    raviolet
    -0.67
    gom
    -0.66
    POSITIVE LOGITS
     institutions
    1.07
     transactions
    1.02
     markets
    1.00
     instruments
    0.97
     sector
    0.97
     derivatives
    0.96
     institution
    0.95
     transaction
    0.94
     intermedi
    0.94
     crisis
    0.91
    Activations Density 0.022%

    No Known Activations