© 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. 4-RES-JB
    11. 10034
    Prev
    Next
    INDEX
    Explanations

    words related to observations or actions involving peeking or looking closely at something

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and participles, particularly those related to observing or looking

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

    No Comments

    Negative Logits
    oled
    -0.74
    blue
    -0.71
    anas
    -0.69
    cour
    -0.68
    gray
    -0.66
    iHUD
    -0.64
    ITIES
    -0.64
    ITS
    -0.64
    ieg
    -0.63
    SO
    -0.63
    POSITIVE LOGITS
     peek
    0.71
    ocene
    0.71
     derog
    0.71
     headlights
    0.70
    lights
    0.68
    hole
    0.67
     Rahul
    0.65
     Editors
    0.64
     afar
    0.63
     passers
    0.63
    Activations Density 0.035%

    No Known Activations