© 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. 10-RES-JB
    11. 7184
    Prev
    Next
    INDEX
    Explanations

    terms related to different physical locations and activities happening in those places

    oai_token-act-pair · gpt-3.5-turbo

    references to natural and social structures, including trees and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ozy
    -0.66
    inventoryQuantity
    -0.65
     Heist
    -0.63
    sych
    -0.61
    antics
    -0.61
    starter
    -0.61
    abus
    -0.60
    ]=
    -0.59
    å¼
    -0.58
    bernatorial
    -0.56
    POSITIVE LOGITS
     nightly
    1.07
     periodically
    1.00
     whenever
    0.98
     anonymously
    0.94
     annually
    0.91
     apiece
    0.85
     wherever
    0.84
     alike
    0.84
     cheaply
    0.84
     tirelessly
    0.82
    Activations Density 0.659%

    No Known Activations