© 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. 13834
    Prev
    Next
    INDEX
    Explanations

    references to historical events or figures

    oai_token-act-pair · gpt-3.5-turbo

    references to historical figures and their contributions

    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
     receivers
    -0.69
     surrender
    -0.69
     sums
    -0.66
     vow
    -0.65
     plat
    -0.64
     infringing
    -0.62
     sender
    -0.62
     indictment
    -0.61
     imprisonment
    -0.61
     Proposition
    -0.61
    POSITIVE LOGITS
    orically
    1.67
    ically
    1.61
    orical
    1.57
    oric
    1.50
    icist
    1.50
    ICAL
    1.47
    ician
    1.45
    icians
    1.44
    orians
    1.38
    ical
    1.36
    Activations Density 0.058%

    No Known Activations