© 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. 23649
    Prev
    Next
    INDEX
    Explanations

    words related to wonder and pondering

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "wonder" and related forms

    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
    ©¶æ
    -0.78
     crawl
    -0.67
     increment
    -0.67
     detainees
    -0.62
    ß
    -0.62
     overrun
    -0.61
     clamp
    -0.61
     retirees
    -0.60
     entrants
    -0.58
     bath
    -0.58
    POSITIVE LOGITS
    onder
    0.99
    ance
    0.91
    aire
    0.88
    oga
    0.88
    ãĤ¤ãĥĪ
    0.84
    enge
    0.81
    ances
    0.79
    ANCE
    0.78
    ason
    0.77
    lich
    0.77
    Activations Density 0.009%

    No Known Activations