© 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. 8-RES-JB
    11. 3282
    Prev
    Next
    INDEX
    Explanations

    references to funeral-related events or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to funerals and related ceremonies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.86
    urat
    -0.72
    yip
    -0.72
    unin
    -0.71
    Cola
    -0.70
    amaru
    -0.69
    umar
    -0.66
    erity
    -0.64
    é¾
    -0.64
    GB
    -0.64
    POSITIVE LOGITS
     procession
    1.19
     rites
    1.08
     crem
    0.92
     shroud
    0.89
     ceremonies
    0.87
     arrangements
    0.86
     rituals
    0.84
     funer
    0.84
     funeral
    0.81
     ceremony
    0.80
    Activations Density 0.057%

    No Known Activations