© 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. 16974
    Prev
    Next
    INDEX
    Explanations

    words related to books and reading

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to book selection and publication

    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
    twitch
    -1.03
     MLG
    -0.89
     GoPro
    -0.88
    gpu
    -0.84
    wcs
    -0.84
    cone
    -0.82
     Qualcomm
    -0.79
     halftime
    -0.77
     DHCP
    -0.76
    merga
    -0.75
    POSITIVE LOGITS
     novels
    2.01
     books
    1.99
     paperback
    1.89
     manuscript
    1.87
     book
    1.85
     literary
    1.82
     Books
    1.76
     manuscripts
    1.69
    books
    1.64
     novelist
    1.63
    Activations Density 0.799%

    No Known Activations