© 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. 8-RES-JB
    11. 17201
    Prev
    Next
    INDEX
    Explanations

    phrases related to hard work and effort

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating effort or hard work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Split
    -0.75
    º
    -0.74
    âĸ¬
    -0.74
    ItemImage
    -0.73
    âĶĢâĶĢ
    -0.73
    GBT
    -0.67
    Found
    -0.65
    Course
    -0.65
    ãĥ¢
    -0.64
    Profile
    -0.64
    POSITIVE LOGITS
     throats
    0.87
     necks
    0.84
    wards
    0.82
     elbows
    0.80
     feathers
    0.75
     oranges
    0.72
     champagne
    0.71
    weed
    0.70
     heels
    0.70
    onite
    0.67
    Activations Density 0.707%

    No Known Activations