© 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. 17831
    Prev
    Next
    INDEX
    Explanations

    references to and mentions of the Philippines

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Philippines

    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
    ership
    -0.82
    ueller
    -0.80
    iquette
    -0.75
    ozyg
    -0.73
    î
    -0.73
    vard
    -0.73
    ivities
    -0.72
    LEASE
    -0.72
    gregation
    -0.68
    ø
    -0.68
    POSITIVE LOGITS
     Philippines
    1.02
     Manila
    0.97
     pes
    0.93
     Duterte
    0.86
     Islands
    0.86
     typh
    0.84
     Philippine
    0.79
     Pes
    0.78
     Rodrigo
    0.75
     Filipino
    0.73
    Activations Density 0.016%

    No Known Activations