© 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. 640
    Prev
    Next
    INDEX
    Explanations

    years or dates

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years, particularly in the mid-20th century

    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
    resso
    -0.77
    tro
    -0.77
    hed
    -0.72
    ithe
    -0.69
    afort
    -0.66
    onet
    -0.63
    hes
    -0.63
    atories
    -0.63
    act
    -0.63
    oat
    -0.63
    POSITIVE LOGITS
    å¹
    0.75
     1946
    0.68
    æ©Ł
    0.66
    çļ
    0.65
     Syndrome
    0.65
     1949
    0.64
     Mechdragon
    0.63
     Fei
    0.63
    chev
    0.62
     Reincarn
    0.62
    Activations Density 0.015%

    No Known Activations