© 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. 11259
    Prev
    Next
    INDEX
    Explanations

    phrases related to amusement park attractions, such as roller coasters, trampolines, and entertainment shows

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly in a personal or contextual sense

    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
     Citizenship
    -0.81
     CRA
    -0.79
     citizenship
    -0.78
     futures
    -0.76
     recip
    -0.76
     coughing
    -0.75
     consulate
    -0.75
     Dal
    -0.75
     Siber
    -0.74
     Predators
    -0.74
    POSITIVE LOGITS
    amp
    2.18
    gt
    1.82
    lt
    1.66
    amps
    1.49
    AMP
    1.41
    asp
    1.21
    amping
    1.21
    span
    1.20
    mp
    1.17
    href
    1.17
    Activations Density 0.042%

    No Known Activations