© 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. 0-RES-JB
    11. 19067
    Prev
    Next
    INDEX
    Explanations

    words related to checks

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of "ques" or related words in a specific context, likely focusing on questioning or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     background
    -0.78
     allergy
    -0.72
     certified
    -0.68
     endorsement
    -0.67
     error
    -0.66
     felony
    -0.64
     cloud
    -0.62
     messenger
    -0.62
     certification
    -0.61
     Elev
    -0.61
    POSITIVE LOGITS
    ques
    4.56
    quez
    1.46
    que
    1.31
    cules
    1.19
    iques
    1.15
    qu
    1.13
    sels
    1.11
    qua
    1.09
    quer
    1.09
    qs
    1.03
    Activations Density 0.005%

    No Known Activations