© 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. 18513
    Prev
    Next
    INDEX
    Explanations

    verbs related to the act of communication

    oai_token-act-pair · gpt-3.5-turbo

    elements related to communication and conveying messages

    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
    sites
    -0.87
    é¾įå
    -0.79
     sidelines
    -0.73
    watch
    -0.67
    veyard
    -0.67
    nea
    -0.63
    ade
    -0.63
    abases
    -0.62
    apers
    -0.62
    kas
    -0.61
    POSITIVE LOGITS
     displeasure
    1.18
     emotion
    1.18
     emotions
    1.17
     feelings
    1.10
     sentiments
    1.07
     truths
    1.02
     ideas
    1.02
     thoughts
    1.01
     messages
    1.00
     gratitude
    0.96
    Activations Density 0.166%

    No Known Activations