© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 16390
    Prev
    Next
    INDEX
    Explanations

    dates or time-related words in the format of "month day"

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods such as months and weeks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Catalog
    -0.72
     Caption
    -0.72
    uddled
    -0.67
    ickle
    -0.66
    rodu
    -0.65
    ickets
    -0.65
    irc
    -0.65
    UTF
    -0.64
    ependent
    -0.64
    alid
    -0.63
    POSITIVE LOGITS
    iatus
    0.87
     ago
    0.84
    ruary
    0.79
     eve
    0.79
     Ago
    0.78
     unbeaten
    0.77
    cture
    0.77
     Marino
    0.75
     Afric
    0.74
     afternoon
    0.74
    Activations Density 0.285%

    No Known Activations