© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 3455
    Prev
    Next
    INDEX
    Explanations

    locations where people have moved to or fled to

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating migration or relocation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.82
     redund
    -0.73
    escent
    -0.72
     certs
    -0.70
     torches
    -0.70
    ŃĶ
    -0.69
    locks
    -0.67
    DragonMagazine
    -0.66
     hairc
    -0.65
    sle
    -0.64
    POSITIVE LOGITS
     Switzerland
    1.41
     Australia
    1.35
     Albania
    1.34
     France
    1.33
     Germany
    1.31
     Belgium
    1.29
     Spain
    1.28
     Italy
    1.27
     Austria
    1.26
     Europe
    1.26
    Activations Density 0.273%

    No Known Activations