© 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. 2836
    Prev
    Next
    INDEX
    Explanations

    sports-related terms, particularly related to player movements and team activities

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, particularly periods that signal the end of statements

    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
    ĸļ
    -0.81
     imagining
    -0.77
     invent
    -0.76
     haunted
    -0.74
     scept
    -0.73
     ingenuity
    -0.73
     dared
    -0.72
    illions
    -0.72
     lately
    -0.71
    obyl
    -0.71
    POSITIVE LOGITS
     Sources
    1.08
    Sources
    1.04
    Prior
    1.02
    According
    1.01
     According
    1.00
     Prior
    0.99
    Statement
    0.99
     Previously
    0.98
    BRE
    0.97
    Assistant
    0.94
    Activations Density 0.341%

    No Known Activations