© 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. 3-RES-JB
    11. 23096
    Prev
    Next
    INDEX
    Explanations

    phrases related to battles and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to "Battle" in contexts related to video games or historical events

    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
    perm
    -0.77
    ĻĤ
    -0.71
    elled
    -0.69
    aunder
    -0.69
    lect
    -0.67
    missible
    -0.67
    itent
    -0.66
    eller
    -0.66
     confir
    -0.64
     fashioned
    -0.64
    POSITIVE LOGITS
     Royale
    1.09
    halla
    1.02
    axe
    1.01
    front
    0.93
     Battle
    0.92
     roy
    0.85
     Battles
    0.83
    mage
    0.82
    Battle
    0.79
     Alliance
    0.76
    Activations Density 0.012%

    No Known Activations