© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 1923
    Prev
    Next
    INDEX
    Explanations

    words related to accidental or unintended actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to accidental or unintended events

    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
    ebus
    -0.78
    eting
    -0.73
    heit
    -0.71
    eters
    -0.70
     Adidas
    -0.70
    yards
    -0.69
    src
    -0.69
    rooms
    -0.69
    ebook
    -0.69
     Tens
    -0.68
    POSITIVE LOGITS
     accidental
    1.16
     unintentional
    1.08
     unintended
    1.02
     consequence
    1.00
    idental
    0.96
    aneous
    0.96
     inadvert
    0.88
     bystand
    0.86
     accidents
    0.82
     consequences
    0.78
    Activations Density 0.011%

    No Known Activations