© 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. 17318
    Prev
    Next
    INDEX
    Explanations

    phrases related to paying attention or showing care and consideration towards something or someone

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of attention, particularly in terms of treating others respectfully and mindfully

    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
    bryce
    -0.68
    latable
    -0.65
    Untitled
    -0.62
    miah
    -0.61
    è¦ļéĨĴ
    -0.61
     hatched
    -0.60
    IED
    -0.60
    iframe
    -0.58
    catentry
    -0.57
     cheaply
    -0.57
    POSITIVE LOGITS
     attention
    1.52
     reverence
    1.32
     respect
    1.31
     regard
    1.28
     scrutiny
    1.27
     consideration
    1.26
     importance
    1.24
     suspicion
    1.24
     esteem
    1.23
     concern
    1.20
    Activations Density 0.269%

    No Known Activations