© 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. 2-RES-JB
    11. 4553
    Prev
    Next
    INDEX
    Explanations

    elements related to user experience (UX) design

    oai_token-act-pair · gpt-3.5-turbo

    terms related to user experience and usability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hood
    -0.89
    bell
    -0.74
    shaw
    -0.74
    SPONSORED
    -0.71
    edly
    -0.70
    cies
    -0.70
     Ago
    -0.66
    stellar
    -0.66
    stals
    -0.65
     Nebula
    -0.64
    POSITIVE LOGITS
     usability
    0.86
    idad
    0.72
    upid
    0.69
    earch
    0.68
    apons
    0.67
    ihad
    0.66
    DEM
    0.65
    ulner
    0.65
    ixels
    0.64
    atsu
    0.64
    Activations Density 0.017%

    No Known Activations