© 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. 7705
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of dating back in history

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating historical references or timelines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
    eye
    -0.63
    reen
    -0.59
    aden
    -0.59
    LLOW
    -0.56
    opal
    -0.56
    rez
    -0.56
    ivo
    -0.55
    =-=-=-=-=-=-=-=-
    -0.54
     lawy
    -0.53
     Spot
    -0.53
    POSITIVE LOGITS
     millennia
    1.10
     centuries
    1.09
     decades
    1.07
     to
    0.96
     millennium
    0.90
    dating
    0.87
     generations
    0.86
    dates
    0.83
     nearly
    0.79
     thousands
    0.78
    Activations Density 0.023%

    No Known Activations