© 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. 8-RES-JB
    11. 3208
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the origin or derivation of names or concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.90
     without
    -0.75
    Downloadha
    -0.75
    anooga
    -0.74
    wd
    -0.73
     thereof
    -0.73
    Enjoy
    -0.66
    adays
    -0.65
    dig
    -0.64
    recy
    -0.64
    POSITIVE LOGITS
     assumption
    1.00
     earliest
    1.00
     simplest
    0.99
     smallest
    0.95
     fact
    0.94
     realm
    0.94
     same
    0.93
     notion
    0.90
     widest
    0.89
     lowest
    0.88
    Activations Density 0.511%

    No Known Activations