© 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. 9-RES-JB
    11. 10273
    Prev
    Next
    INDEX
    Explanations

    numerical time-related phrases such as specific years and time periods

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to time spans in millions or thousands of years

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    usage
    -0.64
     Partner
    -0.63
    UCT
    -0.62
     Demand
    -0.60
     crowds
    -0.60
    _>
    -0.60
     mockery
    -0.59
     landlord
    -0.59
    Demand
    -0.58
     issuer
    -0.58
    POSITIVE LOGITS
     kilometers
    1.41
     miles
    1.36
     kilometres
    1.33
     km
    1.29
    km
    1.22
     mph
    1.09
    years
    1.06
     years
    1.06
     metres
    0.96
     hectares
    0.95
    Activations Density 0.098%

    No Known Activations