© 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. 11-RES-JB
    11. 2283
    Prev
    Next
    INDEX
    Explanations

    specific times and time-related information

    oai_token-act-pair · gpt-3.5-turbo

    time references and scheduling information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resemb
    -0.71
    Bey
    -0.70
    ey
    -0.70
     acknowled
    -0.69
    izations
    -0.61
     Swanson
    -0.61
    proof
    -0.61
    uding
    -0.61
    egu
    -0.60
     hypocr
    -0.60
    POSITIVE LOGITS
     PDT
    1.47
     PST
    1.47
     EST
    1.44
     EDT
    1.44
     CST
    1.33
     ET
    1.30
     PT
    1.27
     BST
    1.25
     CET
    1.22
     GMT
    1.19
    Activations Density 0.044%

    No Known Activations