© 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. 6-RES-JB
    11. 19660
    Prev
    Next
    INDEX
    Explanations

    domain-specific keywords related to pharmaceuticals or medicals services

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and acronyms related to organizations and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leban
    -0.71
    ĨĴ
    -0.68
     Reincarn
    -0.67
    hovah
    -0.66
     thous
    -0.64
     Thunderbolt
    -0.63
    CLASSIFIED
    -0.62
     INCLUD
    -0.61
    landish
    -0.61
     conclud
    -0.60
    POSITIVE LOGITS
    udic
    0.87
    heed
    0.85
    gow
    0.75
    tarians
    0.72
    ibrary
    0.69
    ounge
    0.66
    itte
    0.65
     pockets
    0.65
    ansk
    0.64
    uce
    0.63
    Activations Density 0.539%

    No Known Activations