© 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. 2-RES-JB
    11. 9188
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically related to individuals like public figures

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of individual names, particularly "Kagan" and "Ogan"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upon
    -0.75
     mutual
    -0.68
    Score
    -0.67
    İĭ
    -0.67
     luck
    -0.63
     backlog
    -0.63
    âĢ¢âĢ¢
    -0.63
     apprehension
    -0.62
     abdom
    -0.62
     predictive
    -0.62
    POSITIVE LOGITS
    igans
    1.04
    agan
    1.04
    za
    1.03
    atin
    0.96
    arde
    0.96
    zeb
    0.96
    lein
    0.92
    ocene
    0.91
    azi
    0.88
    itating
    0.87
    Activations Density 0.007%

    No Known Activations