Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 10988
    Prev
    Next
    INDEX
    Explanations

    words related to 'military'

    oai_token-act-pair · gpt-3.5-turbo

    references to military forces and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DAY
    -0.84
    20439
    -0.84
    âĶģ
    -0.79
    upon
    -0.76
    Honest
    -0.76
    ividual
    -0.74
    ï¸
    -0.74
    Jenn
    -0.74
    gger
    -0.73
    heimer
    -0.73
    POSITIVE LOGITS
     fatig
    0.99
     dictatorship
    0.97
     commanders
    0.97
     acad
    0.95
     personnel
    0.95
     readiness
    0.95
     academy
    0.89
     contractor
    0.88
     stationed
    0.87
     garrison
    0.87
    Activations Density 0.034%

    No Known Activations