© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 10636
    Prev
    Next
    INDEX
    Explanations

    phrases related to internet trolls

    oai_token-act-pair · gpt-3.5-turbo

    references to online trolls and trolling behavior

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

    No Comments

    Negative Logits
    ++++++++++++++++
    -0.76
     preservation
    -0.72
     kosher
    -0.62
     cryst
    -0.62
    hani
    -0.62
    earances
    -0.61
    ufact
    -0.61
     nutrit
    -0.60
    erald
    -0.60
     glim
    -0.59
    POSITIVE LOGITS
     trolls
    1.07
     troll
    0.99
    ãĥĦ
    0.89
     trolling
    0.88
     Troll
    0.78
    gren
    0.76
    bag
    0.75
    bags
    0.72
    atsuki
    0.72
    zai
    0.71
    Activations Density 0.008%

    No Known Activations