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. 9-RES-JB
    6. 5094
    Prev
    Next
    INDEX
    Explanations

    phrases related to imagining or fantasizing about different scenarios or things

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to dreaming and aspirations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     citation
    -0.72
    asive
    -0.63
    olitical
    -0.62
    rance
    -0.60
    asions
    -0.58
    ARI
    -0.57
     diff
    -0.56
    avis
    -0.56
     aisle
    -0.56
    ento
    -0.56
    POSITIVE LOGITS
     dreamed
    1.00
    mares
    0.95
     dreams
    0.91
     futures
    0.89
     imagining
    0.89
     envision
    0.89
     visions
    0.89
     aloud
    0.88
     dreaming
    0.86
     imagin
    0.84
    Activations Density 0.132%

    No Known Activations