© 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 EvalsExportsAPI 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. 2025
    Prev
    Next
    INDEX
    Explanations

    the acronym "ETA" followed by a numerical value, most often "9" but sometimes "10"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific data or monetary value

    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
     Mus
    -0.67
     chair
    -0.63
     com
    -0.63
     coin
    -0.62
     jugg
    -0.61
     Swords
    -0.60
     lib
    -0.60
     scr
    -0.58
     heavy
    -0.58
     Os
    -0.58
    POSITIVE LOGITS
    ETA
    4.56
    eta
    1.55
    ERA
    1.38
    ATES
    1.16
    OTA
    1.16
    ENA
    1.12
    ETS
    1.10
    ET
    1.10
    ESA
    1.06
    OTO
    1.06
    Activations Density 0.006%

    No Known Activations