© 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. 20586
    Prev
    Next
    INDEX
    Explanations

    proper names related to sports or events

    oai_token-act-pair · gpt-3.5-turbo

    references to dates, particularly in March

    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
     tray
    -0.69
     Dangerous
    -0.62
     similar
    -0.61
    éĹĺ
    -0.59
     gearing
    -0.59
     nest
    -0.59
    é¾įå¥ij士
    -0.59
     pree
    -0.58
    =]
    -0.57
     bargaining
    -0.57
    POSITIVE LOGITS
    riages
    1.29
    cell
    1.24
    lene
    1.20
    ried
    1.18
    ches
    1.17
    riage
    1.15
    ussia
    1.15
    ques
    1.10
    rying
    1.09
    quez
    1.08
    Activations Density 0.023%

    No Known Activations