© 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. 3030
    Prev
    Next
    INDEX
    Explanations

    time-related phrases or financial terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time intervals measured in years or months

    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
     Borders
    -0.78
    UTF
    -0.67
     ESC
    -0.66
     Nicarag
    -0.64
    HCR
    -0.62
    hemy
    -0.60
    SourceFile
    -0.60
    orem
    -0.60
    anca
    -0.59
     Compass
    -0.59
    POSITIVE LOGITS
    based
    1.12
    time
    1.07
    long
    1.05
    sized
    1.01
    to
    0.97
    years
    0.96
    level
    0.96
    wise
    0.94
    year
    0.92
    gap
    0.92
    Activations Density 0.066%

    No Known Activations