© 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. 7-RES-JB
    11. 11593
    Prev
    Next
    INDEX
    Explanations

    phrases related to cleaning or cleanliness

    oai_token-act-pair · gpt-3.5-turbo

    references to cleaning activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.93
    IFA
    -0.74
     Palin
    -0.71
    sson
    -0.68
    WAY
    -0.68
    enei
    -0.67
    izophren
    -0.67
    abul
    -0.66
    uld
    -0.65
    arsity
    -0.65
    POSITIVE LOGITS
     cleaner
    0.91
    liness
    0.91
     ashore
    0.82
    robe
    0.80
     linen
    0.79
     Clean
    0.78
    clean
    0.74
     cleaners
    0.74
     cloth
    0.73
    se
    0.72
    Activations Density 0.034%

    No Known Activations