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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 21730
    Prev
    Next
    INDEX
    Explanations

    references to the cryptocurrency Bitcoin

    oai_token-act-pair · gpt-3.5-turbo

    references to Bitcoin in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gee
    -0.71
    ¥µ
    -0.71
    spe
    -0.69
    eur
    -0.65
    hurst
    -0.64
    Shin
    -0.63
    lined
    -0.61
    fle
    -0.60
    times
    -0.59
    Finish
    -0.59
    POSITIVE LOGITS
     Bitcoins
    0.99
    ertodd
    0.98
    coins
    0.91
     bitcoins
    0.89
    terness
    0.88
    ruary
    0.80
    rencies
    0.78
    oshenko
    0.77
    aurus
    0.75
    urance
    0.72
    Activations Density 0.010%

    No Known Activations