© 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 EvalsExportsinterp-engineNEWAPI 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. 3400
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or geographic entities

    oai_token-act-pair · gpt-3.5-turbo

    locations and rankings associated with various entities

    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
    raid
    -0.80
    DragonMagazine
    -0.68
    _-
    -0.68
    BILL
    -0.67
    fp
    -0.65
    wcsstore
    -0.65
    rand
    -0.65
     await
    -0.63
    rien
    -0.62
    ictions
    -0.62
    POSITIVE LOGITS
     Europe
    1.26
     existence
    1.20
     America
    1.16
     Asia
    1.10
     Britain
    1.07
     Africa
    1.06
     Canada
    1.04
     Australia
    1.00
     Scandinav
    1.00
     history
    0.98
    Activations Density 0.106%

    No Known Activations