© 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. 0-RES-JB
    11. 19044
    Prev
    Next
    INDEX
    Explanations

    words related to the sun

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Sun."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uffer
    -0.75
    abl
    -0.73
     emb
    -0.66
    Ó
    -0.63
     embr
    -0.62
     Mellon
    -0.62
    ALTH
    -0.62
     advoc
    -0.61
    conom
    -0.61
    iott
    -0.61
    POSITIVE LOGITS
     Sun
    3.95
    Sun
    3.10
    sun
    2.36
     sun
    2.13
     SUN
    1.90
     Thu
    1.58
     Moon
    1.55
     Solar
    1.53
     Sat
    1.50
     Sunrise
    1.48
    Activations Density 0.010%

    No Known Activations