© 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. 4794
    Prev
    Next
    INDEX
    Explanations

    instances of past actions or events expressed with the verb "been" followed by a descriptor or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a state of being or existence over time

    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
    inger
    -0.75
    ors
    -0.64
     Kro
    -0.63
     Chili
    -0.62
    aryl
    -0.61
    ively
    -0.61
    redo
    -0.59
     anymore
    -0.59
    Mario
    -0.59
     Rio
    -0.59
    POSITIVE LOGITS
    keyes
    0.82
     earlier
    0.77
    iless
    0.74
    cffffcc
    0.73
     previously
    0.71
     surg
    0.70
     exha
    0.68
    foreseen
    0.67
     unforeseen
    0.66
     sequest
    0.66
    Activations Density 0.238%

    No Known Activations