© 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. 11-RES-JB
    11. 9498
    Prev
    Next
    INDEX
    Explanations

    phrases indicating knowledge or awareness

    oai_token-act-pair · gpt-3.5-turbo

    references to knowledge or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inqu
    -0.79
    phant
    -0.74
    ãĤ´ãĥ³
    -0.74
    vik
    -0.73
    onding
    -0.65
    cohol
    -0.64
    verse
    -0.64
     sidx
    -0.64
    viks
    -0.64
    reau
    -0.64
    POSITIVE LOGITS
     firsthand
    1.25
     how
    1.19
     instinctively
    1.12
     exactly
    1.11
     better
    1.10
     what
    0.97
     best
    0.96
     intimately
    0.96
     perfectly
    0.91
    how
    0.89
    Activations Density 0.088%

    No Known Activations