© 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. 8-RES-JB
    11. 4285
    Prev
    Next
    INDEX
    Explanations

    numbers related to sports or events

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of motorsports and specific sporting events

    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
     clot
    -0.74
    ront
    -0.69
    anamo
    -0.66
    pex
    -0.64
     Rudolph
    -0.63
    drawn
    -0.62
    è¦ļéĨĴ
    -0.62
    æĪ¦
    -0.61
    rations
    -0.60
    thens
    -0.59
    POSITIVE LOGITS
     royalty
    1.01
     careers
    0.93
     fandom
    0.87
     circles
    0.86
     journalism
    0.83
     enthusiasts
    0.81
     royalties
    0.80
     renaissance
    0.79
     betting
    0.79
     lore
    0.79
    Activations Density 0.252%

    No Known Activations