Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 15447
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "plastic"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of plastic materials and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [|
    -0.74
    ithing
    -0.72
    ---------------
    -0.71
    imov
    -0.71
     VIDE
    -0.69
    aeda
    -0.68
    FontSize
    -0.67
     4090
    -0.66
    llan
    -0.65
    INESS
    -0.65
    POSITIVE LOGITS
     surgery
    1.00
     bags
    0.99
    ity
    0.96
     tubing
    0.92
     filament
    0.92
    ized
    0.91
     Surgery
    0.91
     pellets
    0.90
     surgeons
    0.89
     bottles
    0.88
    Activations Density 0.025%

    No Known Activations