© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23322
    Prev
    Next
    INDEX
    Explanations

    names starting with "De"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "De" followed by any associated numbers or terms

    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
     STEM
    -0.70
     rave
    -0.70
     poppy
    -0.69
     breakthrough
    -0.69
     spur
    -0.67
     pict
    -0.63
     grunt
    -0.62
     MAP
    -0.62
     landmark
    -0.61
     shifts
    -0.61
    POSITIVE LOGITS
    De
    3.70
     De
    2.12
    de
    1.72
    DE
    1.51
    Du
    1.47
     de
    1.40
    Del
    1.32
     DE
    1.30
    Da
    1.26
     DeV
    1.22
    Activations Density 0.010%

    No Known Activations