© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 23187
    Prev
    Next
    INDEX
    Explanations

    references to stories, such as movies, books, or legends

    oai_token-act-pair · gpt-3.5-turbo

    references to "Tale" or "Tales" and related narratives

    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
    ulates
    -0.84
    ressing
    -0.82
    elaide
    -0.81
    ulating
    -0.80
    raper
    -0.77
    itaire
    -0.76
    olicy
    -0.75
    itiz
    -0.72
    ardless
    -0.71
    raft
    -0.71
    POSITIVE LOGITS
     Tale
    1.14
    bringer
    0.84
     Dice
    0.79
     Echoes
    0.75
     Archdemon
    0.75
     Tavern
    0.75
     Hebdo
    0.75
     snipers
    0.74
    âĹ¼
    0.74
     Rise
    0.73
    Activations Density 0.019%

    No Known Activations