© 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. 11-RES-JB
    11. 15687
    Prev
    Next
    INDEX
    Explanations

    keywords related to electronic devices and services, such as e-books, e-readers, e-commerce, and e-mails

    oai_token-act-pair · gpt-3.5-turbo

    references to electronic commerce and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AVG
    -0.84
     Isaac
    -0.78
     AMD
    -0.73
     Anthem
    -0.72
     Cassidy
    -0.69
     Illum
    -0.69
     Bord
    -0.69
     Ernst
    -0.67
     DN
    -0.65
     OPEC
    -0.64
    POSITIVE LOGITS
    mails
    1.89
    mail
    1.82
    commerce
    1.68
    cigarette
    1.61
    cigarettes
    1.49
    liquid
    1.38
    sports
    1.38
    tail
    1.35
    learning
    1.31
    cig
    1.31
    Activations Density 0.030%

    No Known Activations