© 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. 8-RES-JB
    11. 18482
    Prev
    Next
    INDEX
    Explanations

    phrases related to luxurious and indulgent experiences like "fancy hotels" and "expensive meals."

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms associated with luxury and extravagance

    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
    itute
    -0.63
    iciary
    -0.62
    :[
    -0.62
    ¶
    -0.62
    wark
    -0.60
    ajor
    -0.60
    omi
    -0.60
    ACP
    -0.58
    Both
    -0.58
    Å
    -0.58
    POSITIVE LOGITS
     blah
    1.13
     assorted
    1.01
     stuff
    0.90
     everything
    0.81
     maybe
    0.80
     occasional
    0.74
     etc
    0.70
    romeda
    0.70
     endless
    0.70
     lots
    0.69
    Activations Density 0.482%

    No Known Activations