© 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. 1-RES-JB
    11. 20376
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Navy"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Navy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aphael
    -0.70
     SX
    -0.66
     Democr
    -0.66
     Friedrich
    -0.66
     Gree
    -0.65
    èĥ
    -0.65
     DRM
    -0.64
    à¼
    -0.63
    resp
    -0.62
    kj
    -0.62
    POSITIVE LOGITS
     SEAL
    1.19
     Navy
    1.12
     Seal
    1.08
    marine
    0.97
     submar
    0.97
     Yard
    0.90
     sailor
    0.89
     navy
    0.88
     Reserve
    0.86
     Ships
    0.84
    Activations Density 0.005%

    No Known Activations