© 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. 8-RES-JB
    11. 3431
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or scenarios related to military or war

    oai_token-act-pair · gpt-3.5-turbo

    references to battlefields and related warfare concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perm
    -0.79
    clips
    -0.79
    pert
    -0.76
    uana
    -0.74
    bery
    -0.70
    ITY
    -0.69
    credit
    -0.68
    Reviewer
    -0.67
    loo
    -0.67
    iris
    -0.66
    POSITIVE LOGITS
     battlefield
    0.91
     commanders
    0.87
     1942
    0.86
     commander
    0.86
     trenches
    0.81
     1944
    0.79
     combat
    0.77
     1941
    0.74
     discharge
    0.74
     hardened
    0.74
    Activations Density 0.122%

    No Known Activations