© 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. 10141
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by a time-related measure or noun

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time frames or durations for future events

    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
    Reviewer
    -0.80
    dad
    -0.66
    irin
    -0.61
    wegian
    -0.61
     constitu
    -0.59
     perv
    -0.58
    ¿½
    -0.58
     reluct
    -0.56
     knew
    -0.56
    avage
    -0.56
    POSITIVE LOGITS
     2019
    1.58
     2020
    1.54
     2021
    1.52
     2022
    1.42
     2025
    1.41
     2024
    1.41
     future
    1.39
     2018
    1.36
     2030
    1.33
     upcoming
    1.22
    Activations Density 0.230%

    No Known Activations