© 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. 21802
    Prev
    Next
    INDEX
    Explanations

    words related to expressing desires or intentions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or intention

    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
    doms
    -0.57
    natureconservancy
    -0.55
    ulty
    -0.55
     revol
    -0.55
    pole
    -0.52
     Notting
    -0.52
     Lack
    -0.51
     stacked
    -0.51
    usting
    -0.51
     plateau
    -0.50
    POSITIVE LOGITS
     clarification
    0.86
     to
    0.86
     clarify
    0.85
    Disclaimer
    0.83
     congr
    0.79
     readers
    0.78
     apologize
    0.77
     congratulations
    0.76
     reiterate
    0.75
     comment
    0.72
    Activations Density 0.107%

    No Known Activations