© 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. 2-RES-JB
    11. 1038
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Singapore"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Singapore

    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
    20439
    -0.81
    ocaly
    -0.74
    ording
    -0.72
    merce
    -0.71
    urate
    -0.68
    onder
    -0.67
    cause
    -0.66
    BOOK
    -0.65
    ãĤ·ãĥ£
    -0.64
    ×Ļ×
    -0.63
    POSITIVE LOGITS
    apore
    1.11
     Lumpur
    0.99
     Singapore
    0.94
     Airlines
    0.90
    istani
    0.80
     Ling
    0.76
    iang
    0.74
     Chinatown
    0.74
     Tao
    0.71
     Kong
    0.70
    Activations Density 0.007%

    No Known Activations