© 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. 7-RES-JB
    11. 9918
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political figures and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to people, specifically the Turkish President Recep Tayyip Erdogan

    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
     Survivor
    -0.82
     Cena
    -0.75
     Daytona
    -0.74
     Crusade
    -0.73
    Admin
    -0.73
    intern
    -0.70
     Sting
    -0.70
    20439
    -0.69
     Polaris
    -0.69
    aways
    -0.69
    POSITIVE LOGITS
    oÄŁan
    1.36
     Erd
    1.24
     Tayyip
    1.23
    oÄŁ
    1.16
    ı
    1.11
    ÅŁ
    1.09
    istani
    1.06
     Turks
    0.98
    oglu
    0.97
     Erdogan
    0.95
    Activations Density 0.039%

    No Known Activations