© 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. 2-RES-JB
    11. 10427
    Prev
    Next
    INDEX
    Explanations

    mentions of the oldest known or existing entities, such as temples, cities, scriptures, or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to things that are the oldest

    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
    acl
    -0.79
    chy
    -0.78
    rompt
    -0.76
    urrent
    -0.74
    licks
    -0.71
    cci
    -0.71
    intent
    -0.70
    par
    -0.70
    ettings
    -0.70
    action
    -0.69
    POSITIVE LOGITS
     oldest
    0.90
     extant
    0.85
     cousin
    0.76
     daughter
    0.73
     timers
    0.72
     Greatest
    0.72
     timer
    0.71
     gra
    0.70
     answ
    0.70
     surviving
    0.69
    Activations Density 0.004%

    No Known Activations