© 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. 7-RES-JB
    11. 23713
    Prev
    Next
    INDEX
    Explanations

    references to the "Guild Wars" gaming franchise

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

    terms related to the video game "Guild Wars"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etsk
    -0.74
     Devi
    -0.70
    issance
    -0.69
     TED
    -0.68
     Mub
    -0.66
    aneously
    -0.66
    DonaldTrump
    -0.65
     CASE
    -0.64
    ctive
    -0.64
    Downloadha
    -0.62
    POSITIVE LOGITS
    naire
    0.93
    hall
    0.90
    eries
    0.85
    naires
    0.84
    members
    0.84
    busters
    0.82
    mates
    0.81
    hammer
    0.80
    member
    0.78
    hest
    0.78
    Activations Density 0.029%

    No Known Activations