© 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. 3107
    Prev
    Next
    INDEX
    Explanations

    superlatives describing high proficiency or success in various fields, including sports and other professional domains

    oai_token-act-pair · gpt-3.5-turbo

    references to high-performing individuals or athletes across various sports and fields

    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
    tnc
    -0.79
    ãĤ¦ãĤ¹
    -0.66
    çīĪ
    -0.66
     Territories
    -0.62
     unfocusedRange
    -0.61
    ãĥĥ
    -0.61
    inventoryQuantity
    -0.60
    bsp
    -0.59
     srfAttach
    -0.58
    pmwiki
    -0.56
    POSITIVE LOGITS
     alive
    1.40
     ever
    1.10
     EVER
    1.09
     imaginable
    1.04
     Alive
    1.00
     anywhere
    0.91
    ever
    0.82
     afloat
    0.80
     whom
    0.79
     among
    0.76
    Activations Density 0.121%

    No Known Activations