© 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. 9-RES-JB
    11. 4100
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name or entity, "Yatsenyuk"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ats" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.62
    shire
    -0.61
    SPONSORED
    -0.59
     offic
    -0.56
     Tsukuyomi
    -0.56
    SOURCE
    -0.56
     wills
    -0.56
    ADE
    -0.55
    ed
    -0.55
     Ahead
    -0.55
    POSITIVE LOGITS
    rix
    1.11
    rice
    1.11
    terson
    1.04
    ches
    1.04
    ICAN
    1.02
    ting
    1.01
    anooga
    1.01
    hematic
    1.00
    hemat
    1.00
    chers
    0.99
    Activations Density 0.069%

    No Known Activations