Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 19582
    Prev
    Next
    INDEX
    Explanations

    phrases related to official announcements or plans

    oai_token-act-pair · gpt-3.5-turbo

    proposals and announcements related to official plans or legislative actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }.
    -0.52
     proverb
    -0.51
     thri
    -0.49
     alike
    -0.49
    -)
    -0.49
     tends
    -0.49
    fortunately
    -0.48
    !]
    -0.48
     flung
    -0.48
    iuses
    -0.48
    POSITIVE LOGITS
     2019
    0.77
     2021
    0.72
     2020
    0.70
     tomorrow
    0.68
     2018
    0.62
     2024
    0.60
    ESA
    0.59
     Ivanka
    0.55
     indefinite
    0.55
     2022
    0.54
    Activations Density 2.212%

    No Known Activations