© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14526
    Prev
    Next
    INDEX
    Explanations

    phrases related to Bitcoin and blockchain technology

    oai_token-act-pair · gpt-3.5-turbo

    references to Bitcoin and its development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    western
    -0.75
     Outdoor
    -0.73
     Indo
    -0.71
    Finish
    -0.70
     Borders
    -0.69
    alon
    -0.68
     Homeless
    -0.67
    uph
    -0.67
     Curt
    -0.65
     veter
    -0.63
    POSITIVE LOGITS
    rencies
    1.50
    ertodd
    1.18
    coin
    1.17
     ledger
    1.14
    bitcoin
    1.13
     blockchain
    1.12
    urrencies
    1.10
     Bitcoin
    1.10
    Bitcoin
    1.10
    coins
    1.09
    Activations Density 0.232%

    No Known Activations