© 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. 10183
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "shy" in them

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shy" and phrases related to reluctance or avoidance

    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
     Uz
    -0.66
     Alloy
    -0.63
    è¦ļéĨĴ
    -0.62
    RAW
    -0.61
     dism
    -0.60
    Effective
    -0.60
    ãĥķãĤ©
    -0.60
    JUST
    -0.60
    isin
    -0.59
    女
    -0.58
    POSITIVE LOGITS
    vana
    1.20
    sters
    1.09
    ster
    1.04
    ness
    0.96
    nesses
    0.94
    ening
    0.91
    ety
    0.88
    est
    0.87
     away
    0.87
    eness
    0.87
    Activations Density 0.060%

    No Known Activations