© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 7109
    Prev
    Next
    INDEX
    Explanations

    words related to cleaning

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cleaning."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.94
    pton
    -0.68
    NetMessage
    -0.67
    sson
    -0.67
    izophren
    -0.67
    IFA
    -0.67
    ppa
    -0.65
    think
    -0.65
    ussian
    -0.65
    isma
    -0.65
    POSITIVE LOGITS
     cleaner
    0.96
     Clean
    0.82
    liness
    0.81
     ashore
    0.78
     cleaners
    0.78
    clean
    0.77
    ãĤĵ
    0.76
     cleaning
    0.74
     linen
    0.71
     deposit
    0.70
    Activations Density 0.031%

    No Known Activations