Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 16228
    Prev
    Next
    INDEX
    Explanations

    mentions of unintentional events or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to accidents and unintentional events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heit
    -0.89
    ebus
    -0.85
    Tex
    -0.74
    chel
    -0.74
     Tens
    -0.73
    hov
    -0.71
    ebook
    -0.71
    tex
    -0.70
    atche
    -0.70
    rams
    -0.68
    POSITIVE LOGITS
     accidental
    1.10
    aneous
    0.98
    idental
    0.90
     bystand
    0.83
     manslaughter
    0.83
    ities
    0.81
     unintentional
    0.81
     consequence
    0.80
     resurrection
    0.78
     deaths
    0.77
    Activations Density 0.007%

    No Known Activations