© 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. 2499
    Prev
    Next
    INDEX
    Explanations

    events related to someone achieving something for the first time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant first achievements

    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
    bara
    -0.97
     itself
    -0.61
     Else
    -0.61
    mosp
    -0.60
    ribed
    -0.59
    facts
    -0.59
    urus
    -0.59
    models
    -0.59
     Mub
    -0.59
     Sorce
    -0.58
    POSITIVE LOGITS
     foray
    1.04
     Flavoring
    1.03
     consecutive
    0.99
     ever
    0.97
     anniversary
    0.87
     outing
    0.85
     birthday
    0.84
    Ever
    0.84
     appearance
    0.77
     EVER
    0.77
    Activations Density 0.076%

    No Known Activations