© 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. 11-RES-JB
    6. 23131
    Prev
    Next
    INDEX
    Explanations

    references to software bugs and updates

    oai_token-act-pair · gpt-3.5-turbo

    references to bugs or issues in technical contexts, often related to troubleshooting in software or gaming

    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
    Ó
    -0.75
    olitan
    -0.75
     ÂŃ
    -0.72
    Princ
    -0.71
    íķ
    -0.69
    urity
    -0.69
     Tiffany
    -0.68
    RIC
    -0.68
    Pinterest
    -0.67
    nyder
    -0.67
    POSITIVE LOGITS
     respawn
    1.66
     spawn
    1.47
    Spawn
    1.43
     teleport
    1.40
     spawns
    1.38
    spawn
    1.35
     NPCs
    1.35
     Spawn
    1.33
     HUD
    1.28
     spawning
    1.28
    Activations Density 0.375%

    No Known Activations