© 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. 3-RES-JB
    11. 21026
    Prev
    Next
    INDEX
    Explanations

    phrases related to Bitcoin

    oai_token-act-pair · gpt-3.5-turbo

    references to Bitcoin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tainment
    -0.89
    nee
    -0.81
    enegger
    -0.79
    istically
    -0.78
    ufact
    -0.77
     Eisenhower
    -0.74
    ————————
    -0.71
     Prosecut
    -0.69
    ally
    -0.67
    nel
    -0.66
    POSITIVE LOGITS
    cius
    0.86
    rush
    0.83
    USD
    0.81
    ertodd
    0.80
     BTC
    0.79
    osit
    0.78
    ython
    0.78
    hetamine
    0.76
    onz
    0.75
    ategory
    0.75
    Activations Density 0.004%

    No Known Activations