© 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. 9901
    Prev
    Next
    INDEX
    Explanations

    words related to emotions, spirituality, and reflection on personal experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and appreciation for friendship

    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
    SpaceEngineers
    -0.81
     jurisdiction
    -0.68
     Skydragon
    -0.65
    Indust
    -0.64
    Federal
    -0.64
     VAT
    -0.62
    Bench
    -0.61
    Setup
    -0.61
    manufact
    -0.61
    Analy
    -0.61
    POSITIVE LOGITS
     hugs
    1.28
     heartfelt
    1.27
     loving
    1.27
     kindness
    1.25
     tears
    1.19
     kisses
    1.13
     love
    1.13
     gratitude
    1.13
     compassion
    1.12
     sadness
    1.11
    Activations Density 0.862%

    No Known Activations