© 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. 8-RES-JB
    11. 12559
    Prev
    Next
    INDEX
    Explanations

    phrases related to finding or seeking something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" indicating actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.62
    Browser
    -0.60
     Retrieved
    -0.60
     spikes
    -0.57
     reverted
    -0.57
     undefined
    -0.56
    quickShipAvailable
    -0.56
    Got
    -0.56
    Plus
    -0.56
    noticed
    -0.56
    POSITIVE LOGITS
     oversee
    1.33
     whom
    1.20
     accompany
    1.18
     lend
    1.14
     assist
    1.10
     handle
    1.08
     administer
    1.06
     join
    1.05
     help
    1.04
     replace
    1.01
    Activations Density 0.207%

    No Known Activations