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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14499
    Prev
    Next
    INDEX
    Explanations

    technical terms related to military equipment and operations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to military and aerospace 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
    hemy
    -0.76
    ewitness
    -0.74
    olicited
    -0.72
    FORE
    -0.71
    channelAvailability
    -0.71
    employment
    -0.71
    enic
    -0.70
    ngth
    -0.70
    VERSION
    -0.70
    Sales
    -0.69
    POSITIVE LOGITS
     apparatus
    1.33
     system
    1.29
     circuitry
    1.25
     equipment
    1.25
     systems
    1.24
     device
    1.23
     module
    1.23
     devices
    1.18
     mechanism
    1.16
     subsystem
    1.14
    Activations Density 0.380%

    No Known Activations