© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4125
    Prev
    Next
    INDEX
    Explanations

    phrases related to reflecting on past events

    oai_token-act-pair · gpt-3.5-turbo

    references to reflection or nostalgia

    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
     viz
    -0.78
    anto
    -0.67
    iling
    -0.66
    okers
    -0.65
     DEFENSE
    -0.64
     Bunker
    -0.64
     Satanic
    -0.62
     Koch
    -0.60
    pload
    -0.59
    ises
    -0.58
    POSITIVE LOGITS
    wards
    1.09
    dated
    1.07
     nostalg
    1.06
    packs
    1.05
    gam
    0.96
    stab
    0.93
    GROUND
    0.90
    trace
    0.87
    packing
    0.86
    actionDate
    0.82
    Activations Density 0.037%

    No Known Activations