© 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. 19306
    Prev
    Next
    INDEX
    Explanations

    references to different types of currencies

    oai_token-act-pair · gpt-3.5-turbo

    references to official currencies and their status within a country

    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
    Keefe
    -0.78
    hov
    -0.73
    Stage
    -0.71
     Architects
    -0.71
     Ridley
    -0.71
     Stage
    -0.71
     Handler
    -0.70
    Scene
    -0.70
    Jess
    -0.69
     Hels
    -0.69
    POSITIVE LOGITS
     currency
    1.91
     currencies
    1.84
     coins
    1.73
     Currency
    1.62
    currency
    1.61
    rencies
    1.56
     coin
    1.56
     dollar
    1.51
    coins
    1.48
     fiat
    1.47
    Activations Density 0.481%

    No Known Activations