© 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. 11-RES-JB
    11. 22314
    Prev
    Next
    INDEX
    Explanations

    proper nouns referring to people or characters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "The," indicating a focus on introductions or titles in text

    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
    pai
    -0.79
    peak
    -0.71
    æ³
    -0.70
    herer
    -0.69
    estamp
    -0.68
     ï
    -0.67
    rade
    -0.67
    etooth
    -0.66
    Index
    -0.66
    payer
    -0.65
    POSITIVE LOGITS
     sequel
    1.31
     film
    1.21
     screenplay
    1.17
     movie
    1.14
     filmmakers
    1.13
     studio
    1.08
     remake
    1.07
     actress
    1.06
     actor
    1.05
     reboot
    1.05
    Activations Density 0.194%

    No Known Activations