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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 23138
    Prev
    Next
    INDEX
    Explanations

    phrases related to "systems" or "systematic."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to systems and systematic evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pencil
    -0.74
     paternity
    -0.68
     childbirth
    -0.68
     Mens
    -0.68
     swearing
    -0.64
     Hig
    -0.64
     polyg
    -0.63
     delight
    -0.63
     younger
    -0.62
     fetch
    -0.62
    POSITIVE LOGITS
    system
    3.78
    System
    1.73
    ystem
    1.35
    Sys
    1.35
    sys
    1.18
     SYSTEM
    1.12
     systemd
    1.04
    STEM
    1.01
    process
    0.99
     Systems
    0.97
    Activations Density 0.023%

    No Known Activations