© 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. 3-RES-JB
    6. 1831
    Prev
    Next
    INDEX
    Explanations

    words related to maintenance, including upkeep and repair

    oai_token-act-pair · gpt-3.5-turbo

    references to maintenance activities and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    encer
    -0.75
    bern
    -0.75
    xxxxxxxx
    -0.74
     GOODMAN
    -0.72
     Pell
    -0.72
    encers
    -0.71
    HCR
    -0.70
     Colomb
    -0.69
    izons
    -0.68
    ENC
    -0.68
    POSITIVE LOGITS
    tenance
    1.31
     maintenance
    1.20
     upkeep
    1.05
     Maintenance
    0.97
    taker
    0.88
     mathemat
    0.86
     chores
    0.84
     outage
    0.79
     ende
    0.77
     manag
    0.76
    Activations Density 0.010%

    No Known Activations