© 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. 8-RES-JB
    11. 11924
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of stacking or piling objects on top of each other

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to stacking and accumulating items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nton
    -0.82
    bies
    -0.68
    hood
    -0.68
    shire
    -0.67
    generic
    -0.65
    croft
    -0.65
    gnu
    -0.64
    ways
    -0.64
     Lover
    -0.64
    otiation
    -0.63
    POSITIVE LOGITS
     stacked
    0.96
     piles
    0.87
     showc
    0.83
     piled
    0.76
     stacking
    0.76
     shelves
    0.75
     stacks
    0.74
     piling
    0.73
     layers
    0.72
     floors
    0.70
    Activations Density 0.048%

    No Known Activations