© 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. 8-RES-JB
    11. 6964
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific viewpoints or perspectives

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to different perspectives or points of view

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Converted
    -0.64
     incoming
    -0.61
     outgoing
    -0.59
    Ô
    -0.58
     Supplemental
    -0.58
     intrusive
    -0.57
     incorrect
    -0.57
     Shiny
    -0.57
     audible
    -0.56
     redacted
    -0.56
    POSITIVE LOGITS
    piece
    1.07
    otype
    0.98
    coat
    0.95
    pieces
    0.91
    set
    0.90
    aments
    0.89
    share
    0.88
    ament
    0.86
    book
    0.85
    otypes
    0.84
    Activations Density 0.704%

    No Known Activations