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. 8-RES-JB
    6. 1415
    Prev
    Next
    INDEX
    Explanations

    references to criminal activities and scandals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to controversies and scandals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erenn
    -0.82
    requisite
    -0.74
    TeX
    -0.73
     worldly
    -0.71
    ":["
    -0.70
    cms
    -0.69
    heit
    -0.69
    izo
    -0.69
    erd
    -0.69
    cellaneous
    -0.69
    POSITIVE LOGITS
     debacle
    1.26
     fiasco
    1.26
     scandal
    1.05
     massacre
    1.03
     Massacre
    0.96
     spree
    0.95
     controversy
    0.91
     scandals
    0.84
     botched
    0.84
     hoax
    0.84
    Activations Density 0.496%

    No Known Activations