© 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. 10-RES-JB
    11. 3507
    Prev
    Next
    INDEX
    Explanations

    locations or geographical areas

    oai_token-act-pair · gpt-3.5-turbo

    instances of geographic locations or references to places

    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
    ©¶æ
    -0.70
    DragonMagazine
    -0.68
    ionic
    -0.67
    inct
    -0.66
    oyal
    -0.66
    inctions
    -0.65
    agency
    -0.65
    antly
    -0.65
    ¬¼
    -0.64
    itus
    -0.63
    POSITIVE LOGITS
    where
    1.32
    England
    1.27
     where
    1.25
     Switzerland
    1.24
    Mexico
    1.23
     Wales
    1.22
     Europe
    1.20
     Spain
    1.20
     Belgium
    1.20
     Italy
    1.20
    Activations Density 0.247%

    No Known Activations