© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20224
    Prev
    Next
    INDEX
    Explanations

    references to the "Harry Potter" book series

    oai_token-act-pair · gpt-3.5-turbo

    references to the Harry Potter series and its characters

    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
    Texas
    -0.64
     ASA
    -0.63
    MIC
    -0.62
    asio
    -0.62
    ¡
    -0.62
    Low
    -0.60
    IGN
    -0.58
     Ferr
    -0.58
     Fulton
    -0.58
     incent
    -0.57
    POSITIVE LOGITS
     Potter
    1.11
     Dumbledore
    0.94
    uggle
    0.92
     Gand
    0.89
    olkien
    0.88
    ebook
    0.86
     Snape
    0.86
    wra
    0.86
     Hogwarts
    0.86
     Granger
    0.83
    Activations Density 0.060%

    No Known Activations