© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 15556
    Prev
    Next
    INDEX
    Explanations

    business-related terms, including solutions, profits, and connecting community members

    oai_token-act-pair · gpt-3.5-turbo

    subjects related to consumer-oriented businesses and their impact or offerings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.63
     retracted
    -0.61
    oris
    -0.61
    argon
    -0.59
    kat
    -0.58
     retract
    -0.58
     Ratt
    -0.57
     Pastebin
    -0.57
    iban
    -0.56
    arat
    -0.55
    POSITIVE LOGITS
     alike
    1.29
    .</
    0.92
     effortlessly
    0.91
     seamlessly
    0.87
    .","
    0.85
     someday
    0.84
    ãĢĤ
    0.83
     irrespective
    0.83
     regardless
    0.82
     efficiently
    0.81
    Activations Density 0.699%

    No Known Activations