© 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. 0-RES-JB
    11. 5394
    Prev
    Next
    INDEX
    Explanations

    words related to hygiene, often with a focus on cleanliness and health

    oai_token-act-pair · gpt-3.5-turbo

    words related to hygiene and service

    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
     Bagg
    -0.82
     Fallon
    -0.75
    AFTA
    -0.75
     Russo
    -0.74
    ceans
    -0.72
    wikipedia
    -0.71
    antam
    -0.70
    ovo
    -0.70
    GP
    -0.70
    advertising
    -0.68
    POSITIVE LOGITS
     hy
    3.15
     serv
    2.33
     Serv
    1.50
     aph
    1.11
     hydra
    1.09
    serv
    1.02
     ser
    0.99
     servicing
    0.99
     gir
    0.97
    Serv
    0.96
    Activations Density 0.027%

    No Known Activations