© 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. 8-RES-JB
    11. 17676
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific country names, especially Turkey

    oai_token-act-pair · gpt-3.5-turbo

    references to Turkey and its geopolitical actions

    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
    ividual
    -0.77
    ership
    -0.77
    nih
    -0.72
    uckland
    -0.72
     Worcester
    -0.70
    eon
    -0.68
    arial
    -0.67
     Wolver
    -0.66
     McCartney
    -0.66
     Watson
    -0.65
    POSITIVE LOGITS
    istani
    1.19
     Tayyip
    1.09
     Airlines
    0.98
    oglu
    0.89
     Recep
    0.87
    oÄŁan
    0.84
     Ankara
    0.80
    apo
    0.78
     Erdogan
    0.76
    isoft
    0.74
    Activations Density 0.027%

    No Known Activations