© 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. 10-RES-JB
    11. 16560
    Prev
    Next
    INDEX
    Explanations

    words related to public remarks and events

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "the" in various contexts, particularly in reference to events or statements made at specific times

    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
    river
    -0.70
    species
    -0.68
    products
    -0.67
    ister
    -0.67
     whichever
    -0.67
    alties
    -0.66
    tons
    -0.66
    vironments
    -0.66
     resided
    -0.65
     depended
    -0.65
    POSITIVE LOGITS
     outset
    1.24
     ceremony
    1.15
     unveiling
    1.10
     behest
    1.07
     podium
    1.04
     helm
    1.03
     conference
    1.01
     inauguration
    1.00
     briefing
    0.95
     inaugural
    0.92
    Activations Density 0.112%

    No Known Activations