© 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. 8-RES-JB
    11. 3236
    Prev
    Next
    INDEX
    Explanations

    words related to cleaning activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cleaning" and related cleaning actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.95
    sson
    -0.74
    WAY
    -0.73
    ional
    -0.70
    IFA
    -0.66
    aji
    -0.65
    uld
    -0.65
    encers
    -0.65
    BIP
    -0.64
    UGE
    -0.64
    POSITIVE LOGITS
     cleaner
    0.97
    liness
    0.95
     ashore
    0.89
    clean
    0.81
     linen
    0.81
     cleaners
    0.76
    se
    0.75
     slate
    0.74
    robe
    0.74
     Clean
    0.74
    Activations Density 0.047%

    No Known Activations