© 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. 8-RES-JB
    11. 2363
    Prev
    Next
    INDEX
    Explanations

    terms related to scalability issues in technology, particularly focusing on the concept of scalability in the context of Bitcoin and data centers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scalability in systems, particularly in the context of Bitcoin and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruary
    -0.73
    vironment
    -0.71
    urst
    -0.70
    insula
    -0.69
    wich
    -0.69
    riad
    -0.68
    shire
    -0.67
    omes
    -0.67
    landish
    -0.65
    iHUD
    -0.64
    POSITIVE LOGITS
    chio
    0.75
    dot
    0.72
    bucks
    0.71
    iple
    0.69
    ortex
    0.69
    anus
    0.69
    orp
    0.69
    packages
    0.69
    oids
    0.67
     aperture
    0.67
    Activations Density 0.064%

    No Known Activations