© 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. 20486
    Prev
    Next
    INDEX
    Explanations

    words that are anagrams of "as" with varying levels of activation, with higher activations indicating stronger matches

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "as" in various contexts

    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
    «
    -0.63
     Mahjong
    -0.62
     Haram
    -0.62
     Manz
    -0.61
    çīĪ
    -0.60
     Hood
    -0.59
    Ĥª
    -0.59
    Ĺ
    -0.59
     KP
    -0.58
    ghazi
    -0.58
    POSITIVE LOGITS
    ily
    1.04
    iness
    1.03
    urable
    1.02
    enges
    1.00
    orial
    0.92
    orable
    0.89
    ance
    0.89
    antly
    0.88
    uring
    0.87
    ingly
    0.87
    Activations Density 0.111%

    No Known Activations