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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10258
    Prev
    Next
    INDEX
    Explanations

    phrases related to admiration and praise for someone's qualities or abilities

    oai_token-act-pair · gpt-3.5-turbo

    positive traits and characteristics of individuals

    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
     Worse
    -0.89
    pmwiki
    -0.81
     Conclusion
    -0.79
     Alas
    -0.78
     Profit
    -0.76
    utterstock
    -0.75
    è¦ļéĨĴ
    -0.73
     Alternatively
    -0.72
    æ©Ł
    -0.72
     pdf
    -0.71
    POSITIVE LOGITS
     unbelievable
    1.06
     contagious
    1.04
     fearless
    1.01
     infectious
    0.98
     demeanor
    0.96
     personality
    0.92
     mentality
    0.91
     passion
    0.90
     hust
    0.88
     attitude
    0.87
    Activations Density 0.351%

    No Known Activations