Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 24295
    Prev
    Next
    INDEX
    Explanations

    words related to online trolls

    oai_token-act-pair · gpt-3.5-turbo

    references to online trolling and trolls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kosher
    -0.69
     preservation
    -0.66
     Colts
    -0.64
     anesthesia
    -0.63
    ++++++++++++++++
    -0.62
     Continental
    -0.61
     Mavericks
    -0.59
     cider
    -0.59
    EVA
    -0.58
     bonds
    -0.58
    POSITIVE LOGITS
     trolls
    0.97
     troll
    0.93
     trolling
    0.88
    ãĥĦ
    0.86
    tro
    0.78
    gren
    0.75
    ipedia
    0.75
     Troll
    0.75
    atsuki
    0.75
    bag
    0.74
    Activations Density 0.016%

    No Known Activations