Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 20218
    Prev
    Next
    INDEX
    Explanations

    words related to illegal activities or corruption

    oai_token-act-pair · gpt-3.5-turbo

    terms related to illicit activities and schemes, particularly involving "rackets."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plants
    -0.74
     quarters
    -0.70
    illus
    -0.68
    uve
    -0.67
     cand
    -0.66
     sands
    -0.66
     legs
    -0.66
     Plants
    -0.64
     surplus
    -0.63
    houn
    -0.62
    POSITIVE LOGITS
    eering
    1.78
    eer
    1.39
    eers
    1.27
     racket
    1.07
    acket
    0.89
    aminer
    0.84
    esson
    0.80
    nell
    0.78
    zsche
    0.77
    ially
    0.75
    Activations Density 0.019%

    No Known Activations