© 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 EvalsExportsAPI 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. 6-RES-JB
    11. 2561
    Prev
    Next
    INDEX
    Explanations

    technical or mathematical terms related to calculations

    oai_token-act-pair · gpt-3.5-turbo

    references to calculations and numerical evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bley
    -0.79
    Bio
    -0.78
    heimer
    -0.75
    oho
    -0.72
    wood
    -0.72
    VP
    -0.70
    luster
    -0.70
    velt
    -0.70
    ankind
    -0.67
    inki
    -0.66
    POSITIVE LOGITS
     calculation
    1.04
     calculations
    1.00
     equations
    0.94
     calculating
    0.85
     computation
    0.82
     comput
    0.81
     calculate
    0.79
     Calcul
    0.79
    cal
    0.74
     calculated
    0.73
    Activations Density 0.042%

    No Known Activations