Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 10024
    Prev
    Next
    INDEX
    Explanations

    phrases related to the cryptocurrency Bitcoin and its creator Satoshi Nakamoto

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals associated with 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
    rera
    -0.94
    ocal
    -0.86
    aith
    -0.77
    yrus
    -0.74
     McCann
    -0.73
    kson
    -0.73
    lander
    -0.70
    oris
    -0.70
    regon
    -0.69
     Toledo
    -0.68
    POSITIVE LOGITS
     SHA
    1.01
     cryptographic
    0.83
    DoS
    0.78
    DragonMagazine
    0.78
     decaying
    0.75
    Proof
    0.74
     hashing
    0.73
    SHA
    0.72
    Attack
    0.72
     Burr
    0.72
    Activations Density 0.026%

    No Known Activations