© 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. 7240
    Prev
    Next
    INDEX
    Explanations

    proper names related to various topics or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to "The" followed by a noun or proper noun

    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
     beware
    -0.84
     aloud
    -0.80
    ionics
    -0.78
     partake
    -0.74
     forcefully
    -0.69
     stopping
    -0.68
     patiently
    -0.68
    thood
    -0.67
     abound
    -0.66
     recite
    -0.66
    POSITIVE LOGITS
     Hague
    1.18
    odor
    1.16
    atre
    1.14
     Simpsons
    1.11
    orem
    1.11
    oret
    1.09
     Economist
    1.05
     Greatest
    1.01
    aters
    1.00
     Beatles
    1.00
    Activations Density 0.104%

    No Known Activations