© 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. 1-RES-JB
    11. 3207
    Prev
    Next
    INDEX
    Explanations

    references to fiat currency and related financial concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of the word "fiat", especially in the context of currency

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Curiosity
    -0.80
    semble
    -0.73
     Children
    -0.72
    doors
    -0.71
     Roof
    -0.71
    ________________________________
    -0.70
    Dialogue
    -0.70
    older
    -0.70
     Gleaming
    -0.69
    ________________
    -0.69
    POSITIVE LOGITS
     fiat
    1.39
     currencies
    1.11
     currency
    1.04
     banking
    0.91
     Currency
    0.90
     liquidity
    0.89
    entimes
    0.89
     metals
    0.84
     monetary
    0.83
    folios
    0.78
    Activations Density 0.002%

    No Known Activations