© 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. 1-RES-JB
    11. 13091
    Prev
    Next
    INDEX
    Explanations

    references to time periods or durations, particularly measured in years

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "years."

    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
    agonist
    -0.73
    amina
    -0.73
    iqu
    -0.70
     contag
    -0.69
    liction
    -0.67
    ependent
    -0.67
    psey
    -0.65
     plun
    -0.64
    anamo
    -0.63
    atched
    -0.63
    POSITIVE LOGITS
     ago
    1.40
     Ago
    1.22
     olds
    0.87
    åħī
    0.80
    long
    0.75
    manship
    0.75
    glass
    0.72
    mith
    0.72
    à¹
    0.72
    ÙĨ
    0.72
    Activations Density 0.087%

    No Known Activations