© 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. 9-RES-JB
    11. 2378
    Prev
    Next
    INDEX
    Explanations

    references to cryptocurrency, particularly Bitcoin, as well as payment-related terms

    oai_token-act-pair · gpt-3.5-turbo

    keywords associated with Bitcoin and its usage in transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zel
    -0.69
     Saddam
    -0.67
    é¾įå
    -0.66
     Breaker
    -0.62
     Cadillac
    -0.61
    yx
    -0.61
     Rooney
    -0.60
     Izan
    -0.60
    ãĥ´ãĤ¡
    -0.59
     Bearing
    -0.59
    POSITIVE LOGITS
     beginners
    0.73
     mainstream
    0.70
     interact
    0.67
     everyday
    0.66
     unsuspecting
    0.64
    iculture
    0.63
     safely
    0.63
     contexts
    0.63
     anytime
    0.63
     environments
    0.62
    Activations Density 1.124%

    No Known Activations