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

    Neuronpedia

    Jacobian LensNEW
    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. 22108
    Prev
    Next
    INDEX
    Explanations

    titles of books

    oai_token-act-pair · gpt-3.5-turbo

    titles of books or works mentioned in the text

    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
    yright
    -0.70
    hee
    -0.70
    ogle
    -0.69
    idine
    -0.69
    umably
    -0.65
    undai
    -0.64
    rost
    -0.64
    bered
    -0.63
    outube
    -0.62
    respective
    -0.62
    POSITIVE LOGITS
     Lessons
    1.25
     Causes
    1.16
     Bringing
    1.14
     How
    1.13
     Principles
    1.09
     Secrets
    1.09
     Strategies
    1.08
     Stories
    1.08
     Why
    1.07
     Making
    1.05
    Activations Density 0.059%

    No Known Activations