© 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. 6-RES-JB
    11. 20649
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of 'dirty', often in a negative context

    oai_token-act-pair · gpt-3.5-turbo

    references to unethical or illegal activities, particularly involving money and practices described as "dirty."

    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
    -0.97
    */(
    -0.94
    ajor
    -0.85
    iphate
    -0.84
    HCR
    -0.82
    uther
    -0.81
    apult
    -0.79
    ISC
    -0.77
    icultural
    -0.77
    nesota
    -0.77
    POSITIVE LOGITS
     laundry
    1.10
     linen
    0.97
     dirty
    0.86
     mole
    0.83
     tricks
    0.83
     diaper
    0.82
     diapers
    0.79
     stains
    0.78
    bag
    0.76
     cleaner
    0.75
    Activations Density 0.017%

    No Known Activations