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. 7486
    Prev
    Next
    INDEX
    Explanations

    keywords related to scandals

    oai_token-act-pair · gpt-3.5-turbo

    references to scandals

    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
    guyen
    -0.80
    orney
    -0.73
    ignt
    -0.73
    requisite
    -0.72
    ignty
    -0.72
    icrobial
    -0.70
    sterdam
    -0.68
    lasses
    -0.68
    efficients
    -0.68
    yip
    -0.68
    POSITIVE LOGITS
     scandals
    0.96
     scandal
    0.96
    ously
    0.87
    icity
    0.87
     involving
    0.81
     revolving
    0.78
    ous
    0.76
     allegations
    0.75
    uously
    0.70
     Incarn
    0.70
    Activations Density 0.013%

    No Known Activations