© 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. 11-RES-JB
    11. 18771
    Prev
    Next
    INDEX
    Explanations

    words related to exchange rates

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial exchanges and exchange rates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gets
    -0.75
    IGHTS
    -0.72
    owsky
    -0.70
    amia
    -0.65
    jac
    -0.65
    zag
    -0.64
    enegger
    -0.64
    bitious
    -0.63
    ::::::::
    -0.62
    zzle
    -0.60
    POSITIVE LOGITS
     rate
    1.03
     traded
    0.98
    rate
    0.94
     Rates
    0.92
     rates
    0.90
    places
    0.89
     Rate
    0.88
    ability
    0.88
    able
    0.78
    rencies
    0.78
    Activations Density 0.048%

    No Known Activations