© 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. 4-RES-JB
    6. 13375
    Prev
    Next
    INDEX
    Explanations

    references to automated control systems, particularly related to aviation or technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to autopilot systems and references to Jimmy Kimmel

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

    No Comments

    Negative Logits
    itary
    -0.65
     spat
    -0.64
     Amateur
    -0.62
    onductor
    -0.62
     Aliens
    -0.61
     princip
    -0.61
     entrants
    -0.61
    Magikarp
    -0.61
     Martial
    -0.60
    iuses
    -0.60
    POSITIVE LOGITS
    lay
    1.05
    lace
    0.99
    lund
    0.95
    erk
    0.89
    olicy
    0.86
     Eck
    0.85
    ledged
    0.78
    reon
    0.77
    leneck
    0.75
    haw
    0.75
    Activations Density 0.036%

    No Known Activations