© 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. 7-RES-JB
    11. 4422
    Prev
    Next
    INDEX
    Explanations

    specific dates and times mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and times for events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     habit
    -0.73
     grop
    -0.70
     wrongly
    -0.70
     lately
    -0.69
     handwriting
    -0.68
     tended
    -0.66
     hated
    -0.66
     misunderstood
    -0.66
     mistakes
    -0.66
     instinctively
    -0.65
    POSITIVE LOGITS
    Tickets
    1.04
     TBD
    1.00
     TBA
    0.94
     Tickets
    0.91
    2020
    0.84
     Launch
    0.82
     2019
    0.80
    Launch
    0.76
     Mondays
    0.72
    aturdays
    0.71
    Activations Density 0.423%

    No Known Activations