© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 20249
    Prev
    Next
    INDEX
    Explanations

    references to the country of Greece or its related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to Greece and Greek-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eer
    -1.11
    eers
    -0.95
    nels
    -0.87
    DERR
    -0.87
    osterone
    -0.85
    bsp
    -0.83
    ooth
    -0.82
    rence
    -0.82
    eal
    -0.81
    alty
    -0.80
    POSITIVE LOGITS
     traged
    0.82
     Freak
    0.80
     Syri
    0.78
     Greece
    0.77
     islands
    0.73
     crisis
    0.73
     Orthodox
    0.72
     yogurt
    0.72
     Chrys
    0.72
     Athens
    0.72
    Activations Density 0.055%

    No Known Activations