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. 3-RES-JB
    6. 924
    Prev
    Next
    INDEX
    Explanations

    words related to conflict or dispute

    oai_token-act-pair · gpt-3.5-turbo

    references to civility and social conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Leaks
    -0.69
     mosqu
    -0.65
    interstitial
    -0.64
    iffe
    -0.63
     Leopard
    -0.62
     takeaway
    -0.61
     Jacket
    -0.61
    Library
    -0.61
    PORT
    -0.61
    odor
    -0.61
    POSITIVE LOGITS
    ility
    1.17
    ilities
    1.11
    ics
    0.95
    ili
    0.93
    ils
    0.93
    ician
    0.92
    icular
    0.91
    ically
    0.87
    ual
    0.87
    ially
    0.87
    Activations Density 0.021%

    No Known Activations