© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9530
    Prev
    Next
    INDEX
    Explanations

    keywords related to the military, particularly the term "Naval"

    oai_token-act-pair · gpt-3.5-turbo

    references to naval concepts or entities

    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
    à
    -0.82
    upon
    -0.75
    Sax
    -0.74
    oned
    -0.74
    heimer
    -0.73
    bell
    -0.72
    reads
    -0.70
    ħĭ
    -0.70
    à¼
    -0.67
     Lamar
    -0.66
    POSITIVE LOGITS
     naval
    1.09
     Naval
    1.02
     submar
    0.96
    aval
    0.94
     warships
    0.91
    ategory
    0.91
    odon
    0.90
     vessels
    0.88
     Ships
    0.87
    dinand
    0.87
    Activations Density 0.006%

    No Known Activations