© 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. 0-RES-JB
    11. 2340
    Prev
    Next
    INDEX
    Explanations

    phrases related to global or international contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "world."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zik
    -0.81
    abo
    -0.76
    interstitial
    -0.74
    reau
    -0.74
    arson
    -0.69
    ache
    -0.64
    atto
    -0.62
    gran
    -0.62
    Link
    -0.61
    overy
    -0.59
    POSITIVE LOGITS
     world
    3.43
    world
    2.42
     WORLD
    2.40
     worlds
    2.31
    World
    2.10
     World
    2.02
     globe
    1.96
     universe
    1.87
     planet
    1.58
     global
    1.50
    Activations Density 0.053%

    No Known Activations