© 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. 1-RES-JB
    11. 16417
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically starting with the prefix "De"

    oai_token-act-pair · gpt-3.5-turbo

    the proper noun "De" followed by numbers or letters, indicating a specific reference to individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.98
    ĸļ
    -0.96
    sburgh
    -0.90
    ãĢı
    -0.74
     sidx
    -0.73
    DragonMagazine
    -0.73
    ãĤ¤ãĥĪ
    -0.72
     Flavoring
    -0.71
    代
    -0.71
     Kubrick
    -0.69
    POSITIVE LOGITS
    leted
    1.04
    legate
    0.98
    utsch
    0.96
    ja
    0.94
    bris
    0.94
    vel
    0.91
    vers
    0.90
    legates
    0.89
    forestation
    0.84
    epend
    0.83
    Activations Density 0.010%

    No Known Activations