© 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. 14038
    Prev
    Next
    INDEX
    Explanations

    mentions of the cryptocurrency Bitcoin

    oai_token-act-pair · gpt-3.5-turbo

    references to Bitcoin and related topics

    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
     Eisenhower
    -0.80
     Ake
    -0.80
     USAF
    -0.76
     Phant
    -0.71
     Laf
    -0.70
     Pelosi
    -0.68
     Saddam
    -0.68
    gaard
    -0.66
    baugh
    -0.64
    whel
    -0.64
    POSITIVE LOGITS
    rencies
    1.06
    Cash
    1.04
     ATM
    1.02
     transactions
    1.01
     derivatives
    0.99
     ETF
    0.98
     futures
    0.96
    coins
    0.95
    bitcoin
    0.94
     mining
    0.94
    Activations Density 0.030%

    No Known Activations