© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 20457
    Prev
    Next
    INDEX
    Explanations

    phrases related to aspirations or goals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the concept of "dream."

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    avis
    -0.87
     ease
    -0.79
     Methodist
    -0.67
    bidden
    -0.65
     LIA
    -0.64
    iquette
    -0.63
     UCHIJ
    -0.63
    avage
    -0.62
    andise
    -0.62
     Flavoring
    -0.61
    POSITIVE LOGITS
     dream
    1.19
    dream
    1.10
     dreaming
    1.08
     dreamed
    1.05
     dreams
    1.02
    Dream
    1.00
     Dream
    0.93
    scape
    0.92
    tek
    0.88
    hack
    0.82
    Activations Density 0.008%

    No Known Activations