© 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. 10-RES-JB
    11. 11450
    Prev
    Next
    INDEX
    Explanations

    years and seasons mentioned in a temporal context

    oai_token-act-pair · gpt-3.5-turbo

    patterns or sequences related to dates and time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     è£ıè
    -0.81
    rian
    -0.70
     Carm
    -0.69
     Brist
    -0.67
     Sheridan
    -0.64
    rians
    -0.64
    culosis
    -0.63
     Polk
    -0.63
    paio
    -0.62
    ront
    -0.62
    POSITIVE LOGITS
    2001
    1.58
    2002
    1.52
    2003
    1.49
     2001
    1.47
     2002
    1.47
    2004
    1.44
     2003
    1.44
     2004
    1.34
    2000
    1.33
     2000
    1.32
    Activations Density 0.060%

    No Known Activations