© 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. 10-RES-JB
    11. 13656
    Prev
    Next
    INDEX
    Explanations

    the word "a" followed by a word with a positive connotation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" indicating various uses or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unrelated
    -0.63
     establishments
    -0.60
     interests
    -0.60
     orally
    -0.60
     IDs
    -0.60
     events
    -0.59
     unpublished
    -0.59
     rates
    -0.59
     Advanced
    -0.59
     influential
    -0.58
    POSITIVE LOGITS
     tad
    1.40
     bit
    1.31
    flame
    1.10
     little
    1.07
    kward
    1.04
     lot
    1.02
    jar
    1.02
     breeze
    0.99
    versive
    0.97
    gh
    0.96
    Activations Density 0.161%

    No Known Activations