© 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. 4-RES-JB
    11. 525
    Prev
    Next
    INDEX
    Explanations

    dates related to historical events, particularly focusing on the year 1916

    oai_token-act-pair · gpt-3.5-turbo

    references to the year 1916 and related historical events

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

    No Comments

    Negative Logits
    ularity
    -0.76
    iant
    -0.75
    amin
    -0.72
    essee
    -0.71
    iaries
    -0.70
    imon
    -0.70
    egal
    -0.70
    ocks
    -0.68
    ifies
    -0.67
    ographed
    -0.65
    POSITIVE LOGITS
     1916
    0.89
     1914
    0.83
     1915
    0.78
     1917
    0.77
     1918
    0.76
     Osw
    0.74
     Sakuya
    0.72
     1863
    0.71
     Lans
    0.71
     1903
    0.70
    Activations Density 0.011%

    No Known Activations