© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 9123
    Prev
    Next
    INDEX
    Explanations

    ISBN numbers and publishers in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to publishing details, including ISBN numbers and publishing houses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     towed
    -0.75
    bors
    -0.74
     rigs
    -0.74
    xit
    -0.74
    adra
    -0.69
    bones
    -0.69
    amera
    -0.69
    poke
    -0.69
     HUD
    -0.68
    nel
    -0.66
    POSITIVE LOGITS
     paperback
    1.09
     bookstore
    1.08
     ISBN
    1.06
    lisher
    1.05
     Journals
    1.02
    DragonMagazine
    1.02
    Books
    0.99
     Books
    0.97
     Publishing
    0.95
    Writer
    0.93
    Activations Density 0.074%

    No Known Activations