© 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. 0-RES-JB
    11. 1080
    Prev
    Next
    INDEX
    Explanations

    references to Thailand

    oai_token-act-pair · gpt-3.5-turbo

    references to Thailand and its associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gas
    -0.79
     Gas
    -0.76
     haz
    -0.74
    ell
    -0.71
    imer
    -0.70
    gas
    -0.70
     comet
    -0.68
    gall
    -0.67
    ber
    -0.66
     com
    -0.65
    POSITIVE LOGITS
     Thailand
    3.72
     Bangkok
    3.13
     Thai
    2.98
     Cambodia
    2.34
     Laos
    2.31
     Cambod
    2.11
    ailand
    2.07
     Myanmar
    2.07
     Burma
    1.99
     Indonesia
    1.86
    Activations Density 0.026%

    No Known Activations