© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 6925
    Prev
    Next
    INDEX
    Explanations

    words related to being average or slightly below average

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "average" in various contexts

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

    No Comments

    Negative Logits
    aina
    -0.73
    lean
    -0.69
    andro
    -0.68
    lez
    -0.66
    hov
    -0.64
    ystem
    -0.64
    burg
    -0.63
    çīĪ
    -0.63
    resent
    -0.61
     Strateg
    -0.61
    POSITIVE LOGITS
     fastball
    0.87
     GPA
    0.84
     sized
    0.83
     inacc
    0.82
     hourly
    0.78
    imeter
    0.71
    lihood
    0.71
    oday
    0.71
    imate
    0.70
     jo
    0.70
    Activations Density 0.016%

    No Known Activations