© 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. 8196
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific movie or book titled "Dawn"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "Dawn" in various contexts

    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
    ser
    -0.68
    lier
    -0.67
     tou
    -0.67
    sole
    -0.66
     capac
    -0.66
    cer
    -0.65
     sandwic
    -0.64
     ip
    -0.64
     transformer
    -0.64
     sucker
    -0.63
    POSITIVE LOGITS
     Dawn
    4.31
     Dusk
    1.46
    awn
    1.20
     dawn
    1.19
     Ceres
    1.14
     Hearth
    1.13
     Sunrise
    1.09
     Wrath
    1.07
     Willow
    1.07
     Glory
    1.06
    Activations Density 0.019%

    No Known Activations