© 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. 3465
    Prev
    Next
    INDEX
    Explanations

    countries or cities

    oai_token-act-pair · gpt-3.5-turbo

    articles and descriptors related to places or 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
    intent
    -0.78
     announ
    -0.68
    éŃĶ
    -0.68
    é¾įåĸļ士
    -0.66
    bugs
    -0.66
    iew
    -0.66
    dule
    -0.64
    åħī
    -0.64
    insk
    -0.64
    Iterator
    -0.62
    POSITIVE LOGITS
     thriving
    1.05
     vibrant
    1.03
     bustling
    1.00
     bast
    0.97
     stronghold
    0.94
     fertile
    0.93
     formidable
    0.92
     beacon
    0.91
     battleground
    0.90
     hub
    0.88
    Activations Density 0.159%

    No Known Activations