© 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. 10470
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is done or applied exclusively

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "solely."

    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
     Mushroom
    -0.82
     Neighbor
    -0.80
     Signs
    -0.72
     Nurs
    -0.72
    enegger
    -0.71
    Prince
    -0.66
    Doctors
    -0.65
     Patriarch
    -0.62
    lace
    -0.61
     Recession
    -0.60
    POSITIVE LOGITS
     solely
    1.17
     reliant
    0.86
     rely
    0.82
     relied
    0.80
     relying
    0.80
    erred
    0.79
     focused
    0.77
    retion
    0.77
     revolves
    0.75
     purely
    0.74
    Activations Density 0.002%

    No Known Activations