Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 18007
    Prev
    Next
    INDEX
    Explanations

    words related to celestial events like sunrises and sunsets

    oai_token-act-pair · gpt-3.5-turbo

    references to times of day, specifically sunset and sunrise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artments
    -0.82
    byter
    -0.80
    erto
    -0.80
    onne
    -0.77
    DN
    -0.76
    orde
    -0.74
    ongh
    -0.72
    uana
    -0.70
    avanaugh
    -0.69
    enny
    -0.69
    POSITIVE LOGITS
     sunset
    1.29
     sunrise
    1.01
     Sunset
    0.89
    shine
    0.88
    issance
    0.88
     twilight
    0.87
    etheless
    0.82
     Sunrise
    0.80
    ãĤ¤ãĥĪ
    0.77
     reflection
    0.76
    Activations Density 0.008%

    No Known Activations