© 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. 11-RES-JB
    11. 7630
    Prev
    Next
    INDEX
    Explanations

    instances where the word "perfectly" is used in the context of describing actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sense of perfection or acceptability

    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
    rers
    -0.72
    jri
    -0.71
    è¦ļéĨĴ
    -0.69
    SEE
    -0.67
    ulative
    -0.67
    raft
    -0.65
    resy
    -0.64
     extensively
    -0.64
    TRY
    -0.63
    raising
    -0.63
    POSITIVE LOGITS
     suited
    1.07
     timed
    1.06
     positioned
    0.97
     fine
    0.92
     understandable
    0.88
     situated
    0.88
     aligned
    0.87
     calibrated
    0.87
     acceptable
    0.87
     encaps
    0.85
    Activations Density 0.028%

    No Known Activations