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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14901
    Prev
    Next
    INDEX
    Explanations

    phrases related to immigration and movement between different locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" referring to movement or transition

    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
    forcing
    -0.66
    ially
    -0.66
    Directory
    -0.65
    ŃĶ
    -0.65
    ãĤ°
    -0.65
    locking
    -0.64
    icularly
    -0.64
    tun
    -0.64
    acious
    -0.63
    menu
    -0.61
    POSITIVE LOGITS
     England
    1.12
     America
    1.11
     reside
    1.09
     join
    1.09
     Australia
    1.06
     Spain
    1.05
     Canada
    1.03
     Denmark
    1.03
     Sweden
    1.02
     Italy
    1.01
    Activations Density 0.135%

    No Known Activations