© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10038
    Prev
    Next
    INDEX
    Explanations

    dates or time-related events and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to political events and elections

    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
     alias
    -0.67
     mistaken
    -0.66
     pseudonym
    -0.63
     misunderstood
    -0.62
     ingenious
    -0.61
     crou
    -0.60
     dup
    -0.59
    <?
    -0.58
     Perspective
    -0.58
     retweet
    -0.58
    POSITIVE LOGITS
     2019
    1.04
     tomorrow
    1.04
     scheduled
    1.02
     deadlines
    1.00
     next
    1.00
     2022
    0.96
     slated
    0.96
     2020
    0.96
     deadline
    0.95
     2021
    0.93
    Activations Density 0.507%

    No Known Activations