© 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. 2-RES-JB
    11. 9084
    Prev
    Next
    INDEX
    Explanations

    issues related to cleanliness and hygiene, particularly in the context of sanitation and drainage

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to sanitation and hygiene

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.90
    thus
    -0.88
    eton
    -0.84
    lee
    -0.82
    edy
    -0.80
    irin
    -0.76
    NetMessage
    -0.75
    ethe
    -0.73
    zie
    -0.72
    pard
    -0.72
    POSITIVE LOGITS
     sanitation
    1.09
     hygiene
    1.00
    mallow
    0.88
     toilets
    0.88
     cleaner
    0.78
     maintenance
    0.77
     Bunny
    0.76
    bugs
    0.72
     Maintenance
    0.72
    iencies
    0.72
    Activations Density 0.017%

    No Known Activations