© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18622
    Prev
    Next
    INDEX
    Explanations

    verbs indicating the need for action or change

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the need for reforms and urgent actions in various sectors

    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
    interstitial
    -0.67
     unwanted
    -0.64
    owler
    -0.62
     Hilbert
    -0.62
     favorites
    -0.62
     wander
    -0.61
     boredom
    -0.59
     amusement
    -0.59
     fasc
    -0.58
     unlucky
    -0.57
    POSITIVE LOGITS
     ASAP
    1.74
     lest
    1.29
     urgently
    1.25
     sooner
    1.21
     preferably
    1.11
     responsibly
    1.06
     BEFORE
    1.06
     Otherwise
    1.05
     accordingly
    0.90
     Immediately
    0.88
    Activations Density 0.575%

    No Known Activations