© 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. 20345
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a particular time frame or period

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "during" in various contexts and timelines

    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
    onica
    -0.76
    cko
    -0.69
    ettle
    -0.68
    itans
    -0.67
    anship
    -0.66
    adr
    -0.65
    BILITY
    -0.64
    ITH
    -0.63
    amed
    -0.62
    esan
    -0.62
    POSITIVE LOGITS
     periods
    1.17
     renovations
    0.97
     Prohibition
    0.94
     Ramadan
    0.91
     wartime
    0.90
     adolescence
    0.89
     WWII
    0.88
     daylight
    0.87
     infancy
    0.83
     peac
    0.81
    Activations Density 0.067%

    No Known Activations