© 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. 7-RES-JB
    11. 23526
    Prev
    Next
    INDEX
    Explanations

    references to names and positions related to the Air Force

    oai_token-act-pair · gpt-3.5-turbo

    references to the Air Force and related military terminology

    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
    selves
    -0.82
    apest
    -0.80
     Seller
    -0.77
    taboola
    -0.75
    izers
    -0.71
    onym
    -0.70
    spir
    -0.69
    theless
    -0.69
    onymous
    -0.66
    pert
    -0.65
    POSITIVE LOGITS
     Academy
    1.02
     colonel
    1.00
     Awakens
    1.00
     Reserve
    0.99
     Corps
    0.94
     generals
    0.93
     stationed
    0.81
     brass
    0.80
     Base
    0.80
     Intelligence
    0.80
    Activations Density 0.022%

    No Known Activations