© 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
    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. 22818
    Prev
    Next
    INDEX
    Explanations

    terms related to weapons and technology

    oai_token-act-pair · gpt-3.5-turbo

    references to specific products or items, particularly related to darts and the series "Cloak & Dagger."

    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
    phalt
    -0.75
    olulu
    -0.70
    helle
    -0.68
    sis
    -0.68
    crime
    -0.67
    ccording
    -0.67
    undai
    -0.67
    chwitz
    -0.66
     unsolved
    -0.66
    ĻĤ
    -0.66
    POSITIVE LOGITS
     dart
    1.38
     darts
    1.16
     Dart
    0.86
    board
    0.79
    boards
    0.77
     nood
    0.76
    nell
    0.76
    bats
    0.74
    haus
    0.74
     Swim
    0.73
    Activations Density 0.006%

    No Known Activations