© 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. 1743
    Prev
    Next
    INDEX
    Explanations

    references to military personnel, specifically soldiers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of soldiers

    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
    omial
    -0.81
    TERN
    -0.78
    âĶĢâĶĢâĶĢâĶĢ
    -0.77
    aminer
    -0.72
    tera
    -0.72
    Solution
    -0.68
     Bloom
    -0.66
     straw
    -0.66
     Genie
    -0.65
    ologies
    -0.65
    POSITIVE LOGITS
     stationed
    1.20
     fatig
    1.01
     barracks
    0.94
     uniforms
    0.91
     garrison
    0.89
     soldiers
    0.83
     guarding
    0.79
     patrolling
    0.79
     colonel
    0.78
     reserv
    0.78
    Activations Density 0.031%

    No Known Activations