© 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. 1-RES-JB
    11. 10423
    Prev
    Next
    INDEX
    Explanations

    the term "AAA" which typically refers to high credit ratings or quality in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to AAA-rated credit ratings and associated terms

    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
     Manson
    -0.81
    under
    -0.73
    chest
    -0.73
     Dunham
    -0.72
    chen
    -0.71
     Soup
    -0.70
    bird
    -0.67
    oran
    -0.67
     Jenner
    -0.66
    inx
    -0.66
    POSITIVE LOGITS
     AAA
    1.06
    enture
    0.84
    vernment
    0.84
    AAA
    0.79
    ategory
    0.75
    amily
    0.73
    ature
    0.72
     tremend
    0.71
    merce
    0.71
    olicy
    0.71
    Activations Density 0.013%

    No Known Activations