© 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. 20604
    Prev
    Next
    INDEX
    Explanations

    information related to comic books, including issue numbers, character names, and authors

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate authorship or attribution in documents

    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
    ø
    -0.81
    etooth
    -0.81
     Allaah
    -0.80
    hus
    -0.80
    EStream
    -0.79
    youtube
    -0.78
    å
    -0.77
    ntil
    -0.76
     Malays
    -0.74
    okia
    -0.73
    POSITIVE LOGITS
     Comics
    1.86
     comics
    1.67
     comic
    1.47
     Comic
    1.39
     reprint
    1.32
     Marvel
    1.23
     Archie
    1.23
     reprinted
    1.20
     Valiant
    1.17
    Marvel
    1.16
    Activations Density 0.300%

    No Known Activations