© 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. 11201
    Prev
    Next
    INDEX
    Explanations

    gatherings or events where people come together

    oai_token-act-pair · gpt-3.5-turbo

    instances of gatherings and organized protests

    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
    ãĥĥãĥī
    -0.73
     understatement
    -0.69
    ãĤ¦ãĤ¹
    -0.69
    azine
    -0.68
    rss
    -0.66
    Ear
    -0.63
    AAA
    -0.61
    bern
    -0.60
    Fail
    -0.59
     Metatron
    -0.59
    POSITIVE LOGITS
     outside
    1.19
     near
    1.08
     beside
    0.95
     across
    0.94
     atop
    0.92
     amid
    0.92
     roadside
    0.91
     onto
    0.89
     alongside
    0.89
     outdoors
    0.88
    Activations Density 0.335%

    No Known Activations