Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 18846
    Prev
    Next
    INDEX
    Explanations

    terms related to cleanliness and hygiene

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hygiene and sanitation

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

    No Comments

    Negative Logits
    inez
    -0.79
    ¶æ
    -0.73
    NetMessage
    -0.73
    htar
    -0.71
    onga
    -0.70
    horn
    -0.69
    kaya
    -0.68
    pheus
    -0.68
    ozy
    -0.67
    igel
    -0.67
    POSITIVE LOGITS
     hygiene
    1.23
    iencies
    1.04
     sanitation
    0.96
    itary
    0.90
     steril
    0.85
    ufact
    0.81
     cleaner
    0.81
     disinfect
    0.77
     toilets
    0.76
     linen
    0.74
    Activations Density 0.024%

    No Known Activations