© 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. 8-RES-JB
    11. 2581
    Prev
    Next
    INDEX
    Explanations

    quantitative facts and projections related to environmental impacts and economic indicators

    oai_token-act-pair · gpt-3.5-turbo

    numerical data concerning environmental and demographic changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chat
    -0.74
     chats
    -0.73
     arra
    -0.71
     testim
    -0.68
     gossip
    -0.67
     comrade
    -0.66
     DMCA
    -0.66
     teammates
    -0.65
     microphone
    -0.65
     scout
    -0.65
    POSITIVE LOGITS
     2025
    1.35
     2030
    1.34
     2020
    1.32
     2050
    1.32
     2021
    1.22
     2024
    1.16
     someday
    1.10
     2019
    1.06
     2022
    1.04
    2020
    1.02
    Activations Density 0.748%

    No Known Activations