© 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. 1-RES-JB
    11. 6586
    Prev
    Next
    INDEX
    Explanations

    mentions related to historical battles

    oai_token-act-pair · gpt-3.5-turbo

    references to historical battles, particularly their names and occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perm
    -0.83
    missible
    -0.75
    entric
    -0.70
    PF
    -0.68
    hiba
    -0.68
    aunder
    -0.67
    eller
    -0.67
    eva
    -0.65
    ©¶æ
    -0.65
    elled
    -0.64
    POSITIVE LOGITS
    halla
    1.12
     Battle
    1.03
     Royale
    1.01
    axe
    0.95
    Battle
    0.95
     battles
    0.88
    battle
    0.86
     Struggle
    0.85
     roy
    0.85
     Battles
    0.82
    Activations Density 0.011%

    No Known Activations