© 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. 16949
    Prev
    Next
    INDEX
    Explanations

    keywords related to published work, career, or achievements

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "work" or contributions in various contexts

    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
     Ukrain
    -0.97
    wcs
    -0.73
     Cookie
    -0.68
    UGE
    -0.67
     snap
    -0.65
     champagne
    -0.65
     Lod
    -0.63
     Redd
    -0.62
    SPONSORED
    -0.60
     Bubble
    -0.60
    POSITIVE LOGITS
    flows
    1.36
     ethic
    1.35
    manship
    1.32
    aday
    1.26
    station
    1.25
    bench
    1.20
    horse
    1.16
    paces
    1.11
    papers
    1.08
    hops
    1.01
    Activations Density 0.058%

    No Known Activations