© 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. 10-RES-JB
    11. 7801
    Prev
    Next
    INDEX
    Explanations

    expressions of sympathy and support

    oai_token-act-pair · gpt-3.5-turbo

    expressions of sympathy and condolence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yrinth
    -0.76
    é¾
    -0.76
     Dynamics
    -0.72
    existing
    -0.71
     destro
    -0.70
     industrialized
    -0.67
     central
    -0.65
    ulhu
    -0.65
    ahime
    -0.64
     subdiv
    -0.64
    POSITIVE LOGITS
     congratulations
    1.83
     condolences
    1.75
     hugs
    1.69
     compliments
    1.66
     congrat
    1.62
     thank
    1.59
     gratitude
    1.57
     thanking
    1.56
     greeting
    1.55
     kisses
    1.54
    Activations Density 0.523%

    No Known Activations