© 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. 10-RES-JB
    11. 12747
    Prev
    Next
    INDEX
    Explanations

    names of countries or specific locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Czech Republic and related locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aeda
    -0.71
    nels
    -0.71
    Oracle
    -0.71
    natureconservancy
    -0.66
    WARD
    -0.65
     Tasman
    -0.65
     hemor
    -0.64
    xual
    -0.62
    ebus
    -0.62
    inventoryQuantity
    -0.61
    POSITIVE LOGITS
    oslov
    2.01
     Republic
    1.38
    oslav
    1.24
    ski
    1.04
    Republic
    0.99
     Czech
    0.94
    istani
    0.91
    stan
    0.89
     Slov
    0.89
     republic
    0.86
    Activations Density 0.039%

    No Known Activations