© 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. 11-RES-JB
    11. 17671
    Prev
    Next
    INDEX
    Explanations

    locations or regions around the world

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases and connections between countries and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.97
    DragonMagazine
    -0.78
    body
    -0.74
    ulty
    -0.71
     certs
    -0.68
    CRIPTION
    -0.67
    eared
    -0.67
     showc
    -0.67
    ĪĴ
    -0.66
    icipated
    -0.65
    POSITIVE LOGITS
     Denmark
    1.42
     Estonia
    1.41
     Finland
    1.41
     Switzerland
    1.40
     Germany
    1.37
     Scandinav
    1.36
     Afghanistan
    1.36
     Greece
    1.35
     Guatemala
    1.34
     Argentina
    1.33
    Activations Density 0.269%

    No Known Activations