© 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. 2-RES-JB
    11. 8371
    Prev
    Next
    INDEX
    Explanations

    financial terms and company names related to the banking industry

    oai_token-act-pair · gpt-3.5-turbo

    mentions of financial institutions and credit ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ridley
    -0.79
     Atmosp
    -0.76
    umbnail
    -0.72
     Lethal
    -0.70
     Ramos
    -0.66
     Beard
    -0.65
    UV
    -0.65
     tex
    -0.65
     Horus
    -0.65
    ĪĴ
    -0.63
    POSITIVE LOGITS
     banking
    1.24
     banker
    1.18
     securities
    1.16
     liquidity
    1.14
     Securities
    1.14
     brokerage
    1.14
     lender
    1.13
     creditors
    1.10
     hedge
    1.09
     bankers
    1.07
    Activations Density 0.276%

    No Known Activations