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. 6-RES-JB
    6. 22157
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of reversing or reverse actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "reverse" in various contexts

    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
    lished
    -1.10
    Interstitial
    -0.99
    chens
    -0.86
    akov
    -0.77
    akening
    -0.77
    chen
    -0.75
    raltar
    -0.75
    thening
    -0.73
    uana
    -0.73
    liam
    -0.72
    POSITIVE LOGITS
     chronological
    0.93
     engineer
    0.89
    actively
    0.74
     reversal
    0.72
     reversed
    0.70
     reverse
    0.70
     engineered
    0.69
     racism
    0.68
     engineering
    0.68
     sweep
    0.67
    Activations Density 0.015%

    No Known Activations