Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 8860
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Paradise"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'paradise' and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RN
    -0.68
     gest
    -0.66
     ss
    -0.64
    LL
    -0.63
     ACS
    -0.63
     Sung
    -0.62
     Lon
    -0.62
    instein
    -0.62
     scaling
    -0.61
     rs
    -0.61
    POSITIVE LOGITS
     Paradise
    3.24
     paradise
    2.47
    estate
    1.66
    cape
    1.58
    istan
    1.21
     Mile
    1.03
    pour
    1.02
     Exile
    0.99
     Treasure
    0.94
     Eden
    0.90
    Activations Density 0.034%

    No Known Activations