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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RES-JB
    6. 15241
    Prev
    Next
    INDEX
    Explanations

    descriptions of various actions and events related to navigation and transportation

    oai_token-act-pair · gpt-3.5-turbo

    elements related to navigation and communication systems in a military or emergency context

    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
    LGBT
    -0.79
    chool
    -0.78
    hemy
    -0.77
    soType
    -0.76
    mopolitan
    -0.75
    iberal
    -0.75
     vend
    -0.75
     boycot
    -0.73
     Cities
    -0.72
    basketball
    -0.72
    POSITIVE LOGITS
     Flight
    1.37
    Flight
    1.37
    ilot
    1.35
     cockpit
    1.32
     pilots
    1.24
     aboard
    1.20
    ircraft
    1.19
    flight
    1.19
    Engineers
    1.18
     onboard
    1.17
    Activations Density 0.492%

    No Known Activations