© 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. 11-RES-JB
    11. 6772
    Prev
    Next
    INDEX
    Explanations

    phrases related to military activities and operations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to security and military operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cients
    -0.74
     liar
    -0.71
     narrator
    -0.70
     exception
    -0.67
    etheless
    -0.67
     typo
    -0.66
     bartender
    -0.65
     spoiled
    -0.65
     attacker
    -0.64
    epad
    -0.63
    POSITIVE LOGITS
     activities
    1.64
     exercises
    1.42
     tasks
    1.41
     missions
    1.39
     operations
    1.38
     pursuits
    1.34
     campaigns
    1.31
     endeavors
    1.31
     experiments
    1.30
     ceremonies
    1.29
    Activations Density 0.435%

    No Known Activations