© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18742
    Prev
    Next
    INDEX
    Explanations

    occurrences of durations of time expressed in years

    oai_token-act-pair · gpt-3.5-turbo

    references to durations of time, particularly in years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hest
    -0.65
     helicop
    -0.64
     Helpful
    -0.64
     Rooms
    -0.63
    cair
    -0.63
     GOODMAN
    -0.62
    ufficient
    -0.61
    alos
    -0.61
    achus
    -0.60
    redients
    -0.59
    POSITIVE LOGITS
     anniversary
    1.24
     hiatus
    0.92
    iversary
    0.90
     lifespan
    0.90
     ago
    0.89
     span
    0.89
     period
    0.89
     itch
    0.87
     reign
    0.87
     relationship
    0.86
    Activations Density 0.041%

    No Known Activations