© 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. 9-RES-JB
    11. 10019
    Prev
    Next
    INDEX
    Explanations

    phrases referring to a majority or a high frequency of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "most" indicating commonality or majority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rompt
    -0.91
    edin
    -0.70
    icer
    -0.66
    thora
    -0.66
    wings
    -0.65
    hawk
    -0.63
    orld
    -0.62
    moil
    -0.62
    Report
    -0.61
    alid
    -0.61
    POSITIVE LOGITS
     importantly
    0.97
    afa
    0.87
     mornings
    0.82
     workplaces
    0.78
     sane
    0.78
     observers
    0.78
     Americans
    0.77
     cases
    0.77
     of
    0.75
    THING
    0.75
    Activations Density 0.050%

    No Known Activations