© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 14987
    Prev
    Next
    INDEX
    Explanations

    words related to complaints or grievances

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "complaint" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shock
    -0.71
    odes
    -0.64
     Spoiler
    -0.63
    ECD
    -0.63
    arta
    -0.63
    isse
    -0.63
    tan
    -0.62
    natureconservancy
    -0.62
    intage
    -0.61
    ano
    -0.61
    POSITIVE LOGITS
     lodged
    1.25
     alleging
    1.16
     about
    1.05
     filed
    1.01
    naires
    1.00
     against
    0.99
     complaints
    0.96
     leve
    0.94
     ABOUT
    0.91
    naire
    0.86
    Activations Density 0.069%

    No Known Activations