© 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. 10-RES-JB
    11. 19082
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to observing, watching, or looking at something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "pe" 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
    enegger
    -0.72
    shire
    -0.66
    picture
    -0.65
    IFT
    -0.60
    INGTON
    -0.57
     Thrones
    -0.57
     EDITION
    -0.55
     trapping
    -0.55
     Paste
    -0.55
     Pulse
    -0.55
    POSITIVE LOGITS
    eking
    1.19
    formance
    1.18
    eps
    1.18
    eping
    1.18
    gging
    1.15
    cking
    1.11
    ggy
    1.09
    pperc
    1.07
    gged
    1.05
    ptic
    1.04
    Activations Density 0.019%

    No Known Activations