© 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. 13742
    Prev
    Next
    INDEX
    Explanations

    specific references to the word "Bott" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    references to "bottled" products or entities

    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
    è¦ļéĨĴ
    -0.74
    ãĥĵ
    -0.74
    isable
    -0.69
     Skydragon
    -0.66
    itably
    -0.63
    ITED
    -0.60
    ãĤ¤ãĥĪ
    -0.59
    ãĥ³ãĤ¸
    -0.59
     computer
    -0.59
    incible
    -0.58
    POSITIVE LOGITS
    leneck
    1.16
    ewater
    1.11
    len
    0.94
    hest
    0.91
    oms
    0.90
    yl
    0.87
    les
    0.87
    rell
    0.86
    esy
    0.86
    orius
    0.83
    Activations Density 0.071%

    No Known Activations