© 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. 569
    Prev
    Next
    INDEX
    Explanations

    years in the 1940s

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years in the mid-20th century, particularly the years 1947, 1948, and 1949

    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
    hed
    -0.81
    tro
    -0.79
    onet
    -0.75
    andering
    -0.74
    anders
    -0.68
    Nation
    -0.67
    resso
    -0.65
    ander
    -0.65
    Kin
    -0.64
    ithe
    -0.64
    POSITIVE LOGITS
     1946
    0.91
     1949
    0.86
     1954
    0.85
     1953
    0.85
     1957
    0.85
     1947
    0.84
     1958
    0.83
     1952
    0.83
     1955
    0.82
     1956
    0.81
    Activations Density 0.016%

    No Known Activations