© 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. 2-RES-JB
    11. 12686
    Prev
    Next
    INDEX
    Explanations

    mentions of the Windows operating system version XP and its various features such as XP9, XP8, Vista, queries, passwords, enhancements, and installations

    oai_token-act-pair · gpt-3.5-turbo

    references to experience points (XP) in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĸ¬âĸ¬
    -0.77
    ker
    -0.67
    ãĥŀ
    -0.65
    gie
    -0.64
    66666666
    -0.64
    ãĥĦ
    -0.63
     Nicola
    -0.62
    maid
    -0.62
     Cumber
    -0.61
    ters
    -0.61
    POSITIVE LOGITS
     XP
    0.88
    uria
    0.87
    XP
    0.84
    rowth
    0.82
    onential
    0.82
    resso
    0.80
    ionage
    0.80
    ORPG
    0.78
    etition
    0.78
    aques
    0.77
    Activations Density 0.012%

    No Known Activations