© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 11461
    Prev
    Next
    INDEX
    Explanations

    keywords related to global affairs and the world's status in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "world" and its various implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    veyard
    -1.14
    ippi
    -0.87
    sbm
    -0.76
    paio
    -0.75
    ibility
    -0.75
    yrinth
    -0.75
    Ô
    -0.74
    conserv
    -0.73
    uffer
    -0.72
    iple
    -0.71
    POSITIVE LOGITS
     economy
    1.01
     proletariat
    0.90
    econom
    0.84
     treaty
    0.81
    wide
    0.81
     treaties
    0.79
     Economy
    0.79
     superpower
    0.77
     nations
    0.76
     diplomat
    0.76
    Activations Density 0.069%

    No Known Activations