© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3-RES-JB
    11. 16959
    Prev
    Next
    INDEX
    Explanations

    phrases related to complex interactions or processes

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to dynamics in various contexts

    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
    unts
    -0.85
    iverpool
    -0.78
    gement
    -0.77
    azar
    -0.75
    chens
    -0.74
    anas
    -0.72
    inker
    -0.72
    istle
    -0.71
    glas
    -0.71
    itude
    -0.70
    POSITIVE LOGITS
     dynamics
    1.00
     equations
    0.92
     equation
    0.91
     fluctuations
    0.78
     Stability
    0.75
    odynamics
    0.74
     instability
    0.74
     stabilization
    0.71
     turbulence
    0.71
    anship
    0.70
    Activations Density 0.013%

    No Known Activations