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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 1118
    Prev
    Next
    INDEX
    Explanations

    years in the context of events or actions happening in that year

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the year 2018

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sov
    -0.68
     traced
    -0.68
     chim
    -0.67
     [*
    -0.67
     concede
    -0.67
    SPONSORED
    -0.65
    JB
    -0.65
     paralle
    -0.62
     pat
    -0.61
    ith
    -0.61
    POSITIVE LOGITS
     2018
    3.76
     2019
    2.96
    2018
    2.92
     2017
    2.61
     2020
    2.31
     2021
    2.23
     2022
    2.21
     2016
    2.17
    2017
    2.01
     2024
    2.00
    Activations Density 0.012%

    No Known Activations