© 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. 22885
    Prev
    Next
    INDEX
    Explanations

    specific dates, times, and events mentioned in text passages

    oai_token-act-pair · gpt-3.5-turbo

    specific dates or times associated with 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
    yt
    -0.76
    tab
    -0.66
    Ds
    -0.64
    Adapter
    -0.63
     usefulness
    -0.61
     resists
    -0.60
    Credits
    -0.59
    ifted
    -0.59
    dies
    -0.58
    argo
    -0.58
    POSITIVE LOGITS
     Ples
    0.78
    retty
    0.69
     March
    0.68
     conjunction
    0.65
     February
    0.65
     Auburn
    0.64
    GMT
    0.64
     Canaver
    0.62
     Sharif
    0.62
     Peel
    0.61
    Activations Density 0.351%

    No Known Activations