© 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. 7-RES-JB
    11. 20815
    Prev
    Next
    INDEX
    Explanations

    mentions of military settings or strategies

    oai_token-act-pair · gpt-3.5-turbo

    references to battlefields and battlegrounds in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ola
    -0.84
    uana
    -0.82
    arent
    -0.82
    andro
    -0.80
    legate
    -0.79
    oras
    -0.77
    quer
    -0.76
    atra
    -0.76
    alez
    -0.76
    der
    -0.74
    POSITIVE LOGITS
    halla
    0.72
     swall
    0.71
    ãĤ§
    0.70
     Advantage
    0.70
     battlefield
    0.69
     mornings
    0.68
     Ready
    0.68
     brawl
    0.66
     swings
    0.65
    front
    0.65
    Activations Density 0.053%

    No Known Activations