© 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 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. 11-RES-JB
    11. 15018
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific substance as a solution for pain relief

    oai_token-act-pair · gpt-3.5-turbo

    references to significant political or societal influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sheets
    -0.53
     anecd
    -0.51
    ogie
    -0.50
    oqu
    -0.50
     exasper
    -0.50
     amazed
    -0.48
    quartered
    -0.48
     misplaced
    -0.47
    athered
    -0.47
    bare
    -0.46
    POSITIVE LOGITS
     2019
    0.92
     2020
    0.85
     someday
    0.83
     2024
    0.82
    morrow
    0.80
     2022
    0.79
     2021
    0.78
     future
    0.74
     2018
    0.72
    Brexit
    0.70
    Activations Density 1.030%

    No Known Activations