© 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. 1-RES-JB
    11. 24204
    Prev
    Next
    INDEX
    Explanations

    phrases related to luxury and desire

    oai_token-act-pair · gpt-3.5-turbo

    references to luxury and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¶ħ
    -0.80
    SHIP
    -0.78
    brush
    -0.66
    BOOK
    -0.65
    udeb
    -0.64
    wart
    -0.64
    warts
    -0.64
    ãĢİ
    -0.64
     Rough
    -0.64
    UGC
    -0.61
    POSITIVE LOGITS
    uries
    1.27
    ury
    1.20
    urious
    1.13
    lux
    1.02
     Lux
    0.91
    iliary
    0.88
    rete
    0.87
    isse
    0.86
    enses
    0.86
    ancies
    0.83
    Activations Density 0.007%

    No Known Activations