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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 16076
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or activities taking place in specific venues

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Arena" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FORMATION
    -0.71
    dit
    -0.70
    arent
    -0.70
    armed
    -0.69
    nir
    -0.69
    ths
    -0.68
    orders
    -0.68
    teenth
    -0.68
    eling
    -0.68
    nee
    -0.65
    POSITIVE LOGITS
    Net
    0.94
    Aren
    0.92
     Arena
    0.89
     Royale
    0.82
     Squadron
    0.78
    adium
    0.77
     arena
    0.76
     Coliseum
    0.75
     Plaza
    0.73
     arenas
    0.72
    Activations Density 0.005%

    No Known Activations