© 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. 3-RES-JB
    11. 9444
    Prev
    Next
    INDEX
    Explanations

    the first name "De" with an emphasis on different variations

    oai_token-act-pair · gpt-3.5-turbo

    the mention of a specific individual or character, likely related to a narrative or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -1.15
    uyomi
    -0.90
    ãĤ¤ãĥĪ
    -0.89
    DragonMagazine
    -0.82
     Flavoring
    -0.81
    sburgh
    -0.81
    hetti
    -0.79
     sidx
    -0.77
    allery
    -0.72
    代
    -0.71
    POSITIVE LOGITS
    legate
    1.14
    leted
    1.10
    utsch
    1.09
    legates
    1.05
    arest
    1.00
    vers
    0.98
    classified
    0.96
    qu
    0.93
    bris
    0.92
    VICE
    0.92
    Activations Density 0.014%

    No Known Activations