© 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. 6-RES-JB
    11. 18392
    Prev
    Next
    INDEX
    Explanations

    instances of phrases indicating a "first time" event

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the occurrence of events for the first time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asty
    -0.86
    ote
    -0.73
     tomat
    -0.66
    bern
    -0.66
    Dri
    -0.61
    CHAT
    -0.60
     Mole
    -0.60
    asted
    -0.60
    ophe
    -0.59
    otten
    -0.59
    POSITIVE LOGITS
    ever
    0.84
     EVER
    0.78
     imaginable
    0.77
     ever
    0.75
     domestically
    0.69
    imester
    0.66
     anniversary
    0.64
    Ever
    0.63
     practicable
    0.62
     since
    0.62
    Activations Density 0.027%

    No Known Activations