© 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. 17672
    Prev
    Next
    INDEX
    Explanations

    references to the material "plastic."

    oai_token-act-pair · gpt-3.5-turbo

    references to plastic materials and their usage

    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
    ---------------
    -0.72
     [|
    -0.71
    FontSize
    -0.69
    ithing
    -0.67
    inen
    -0.67
    aternity
    -0.66
    imov
    -0.66
    awar
    -0.66
    unct
    -0.65
     VIDE
    -0.63
    POSITIVE LOGITS
     tubing
    0.96
     surgery
    0.95
     bags
    0.94
     filament
    0.90
     pellets
    0.89
     bottles
    0.86
     plastic
    0.85
    ity
    0.85
     dioxide
    0.85
     wrap
    0.83
    Activations Density 0.027%

    No Known Activations