© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4693
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to historical events, particularly wars and military activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of wars referenced in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DERR
    -0.65
     caution
    -0.62
    say
    -0.62
    APS
    -0.60
     sher
    -0.59
     suspic
    -0.58
     predictive
    -0.58
     clutch
    -0.58
     pert
    -0.57
     surpr
    -0.57
    POSITIVE LOGITS
     II
    1.36
     Two
    1.16
     III
    0.96
     One
    0.92
     ii
    0.84
     XII
    0.83
     VII
    0.81
    II
    0.81
     Three
    0.81
    planes
    0.81
    Activations Density 0.042%

    No Known Activations