© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5291
    Prev
    Next
    INDEX
    Explanations

    verbs related to using time or resources

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "spent."

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    inguishable
    -0.63
    ected
    -0.63
    forward
    -0.62
    peer
    -0.62
    eq
    -0.61
     Seymour
    -0.60
    uana
    -0.60
    abol
    -0.60
    ablo
    -0.59
    uber
    -0.58
    POSITIVE LOGITS
     Spend
    0.97
     spent
    0.96
    itures
    0.95
     lav
    0.93
     Spending
    0.83
     IPM
    0.78
     redes
    0.76
    iture
    0.76
     spend
    0.75
    kson
    0.74
    Activations Density 0.017%

    No Known Activations