© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 24079
    Prev
    Next
    INDEX
    Explanations

    items or activities that require cleaning

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of cleaning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pton
    -0.73
    peak
    -0.68
    yip
    -0.67
    bra
    -0.66
    sson
    -0.66
    CVE
    -0.64
    uld
    -0.64
    WAY
    -0.64
    arsity
    -0.63
    waves
    -0.62
    POSITIVE LOGITS
     cleaner
    1.09
     cleaning
    1.03
     cleaners
    1.02
     Clean
    0.96
     cleanup
    0.95
    clean
    0.89
    Clean
    0.84
     laundry
    0.74
     cleaned
    0.74
     linen
    0.72
    Activations Density 0.015%

    No Known Activations