© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7584
    Prev
    Next
    INDEX
    Explanations

    phrases related to time spans, particularly the word "decade."

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, specifically decades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ases
    -0.67
    press
    -0.64
    oke
    -0.62
     checks
    -0.60
    ouk
    -0.59
    Instruct
    -0.58
     Orders
    -0.58
    lamm
    -0.57
     Sto
    -0.57
    info
    -0.57
    POSITIVE LOGITS
     decade
    3.31
     century
    2.11
     decades
    1.97
     millennium
    1.80
     year
    1.71
    century
    1.59
     YEAR
    1.52
     years
    1.48
    Years
    1.42
     Century
    1.41
    Activations Density 0.016%

    No Known Activations