© 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. 17716
    Prev
    Next
    INDEX
    Explanations

    comic book titles and issue numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to comic book issues and related numbers

    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
    isance
    -0.86
    etooth
    -0.75
    onomous
    -0.74
    footed
    -0.73
    fulness
    -0.71
    chuk
    -0.69
    ghazi
    -0.68
    idity
    -0.68
     def
    -0.68
    isy
    -0.67
    POSITIVE LOGITS
     Comics
    1.20
     reprint
    1.14
     comics
    1.03
    lisher
    1.02
     anthology
    0.98
     reprinted
    0.91
     manga
    0.91
     adaptations
    0.88
     Comic
    0.86
     Anth
    0.84
    Activations Density 0.152%

    No Known Activations