© 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. 9236
    Prev
    Next
    INDEX
    Explanations

    information about different currencies and currency exchange

    oai_token-act-pair · gpt-3.5-turbo

    references to currencies, particularly the Cuban peso and the U.S. dollar

    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
    missions
    -0.73
    Stage
    -0.72
    task
    -0.72
    Scene
    -0.71
    Keefe
    -0.71
    terior
    -0.69
    beard
    -0.67
    Site
    -0.67
    becue
    -0.65
     Networks
    -0.65
    POSITIVE LOGITS
     currencies
    1.68
     currency
    1.60
     dollar
    1.49
     fiat
    1.46
     yen
    1.44
     pes
    1.40
     Currency
    1.37
     sterling
    1.37
     yuan
    1.37
     Dollar
    1.35
    Activations Density 0.336%

    No Known Activations