© 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. 23672
    Prev
    Next
    INDEX
    Explanations

    references to time periods, specifically the past

    oai_token-act-pair · gpt-3.5-turbo

    references to time, especially past events

    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
    anguage
    -0.81
    Software
    -0.74
    hz
    -0.72
    hyde
    -0.68
    Services
    -0.64
    shapeshifter
    -0.64
    NEY
    -0.63
    igion
    -0.63
    witz
    -0.63
    horn
    -0.63
    POSITIVE LOGITS
    ebin
    1.38
     tense
    0.94
    iche
    0.90
     generations
    0.85
     past
    0.78
     week
    0.76
     midnight
    0.76
     decade
    0.72
    ures
    0.67
    ime
    0.67
    Activations Density 0.031%

    No Known Activations