© 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. 6-RES-JB
    11. 11817
    Prev
    Next
    INDEX
    Explanations

    instances of the term "DE" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the acronym "DE" related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocene
    -0.93
    olulu
    -0.83
    toggle
    -0.81
     BaseType
    -0.78
    ãĤ¤ãĥĪ
    -0.74
    imity
    -0.74
    beans
    -0.73
     è£ıè¦ļéĨĴ
    -0.71
    aceous
    -0.71
    hetti
    -0.70
    POSITIVE LOGITS
    VICE
    1.21
    FAULT
    1.18
    FIN
    1.14
    FINE
    0.99
    POS
    0.97
    PUT
    0.95
    PRESS
    0.91
    VEL
    0.85
    ER
    0.84
    PART
    0.82
    Activations Density 0.017%

    No Known Activations