© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 14469
    Prev
    Next
    INDEX
    Explanations

    words or parts of words related to "ont" or "ontrol"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "content," specifically items classified as such

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pigs
    -0.66
    GBT
    -0.65
    âĻ¥
    -0.58
     JPM
    -0.58
     CTR
    -0.58
     Rahman
    -0.58
    ITED
    -0.57
    TOP
    -0.57
    ging
    -0.57
    glers
    -0.57
    POSITIVE LOGITS
    rol
    1.32
    ario
    1.20
    ology
    1.19
    inent
    1.18
    ological
    1.18
    gomery
    1.08
    anus
    1.07
    rovers
    1.06
    ologist
    1.06
    ainment
    1.04
    Activations Density 0.058%

    No Known Activations