© 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. 17815
    Prev
    Next
    INDEX
    Explanations

    phrases related to observing or being present for events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "witness" and its variations

    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
    quote
    -0.85
    govtrack
    -0.81
    starter
    -0.80
    ulum
    -0.74
    hp
    -0.73
    sheet
    -0.68
    bags
    -0.66
    kick
    -0.66
     drawer
    -0.66
    ularity
    -0.64
    POSITIVE LOGITS
     firsthand
    1.42
     unfold
    0.99
     unfolding
    0.91
     pandemonium
    0.85
     events
    0.85
     witnessing
    0.85
    Events
    0.84
     atrocities
    0.81
     horrors
    0.81
    ewitness
    0.81
    Activations Density 0.091%

    No Known Activations