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. 1-RES-JB
    6. 13594
    Prev
    Next
    INDEX
    Explanations

    references to technical nodes or elements in a system

    oai_token-act-pair · gpt-3.5-turbo

    mentions of network nodes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aternity
    -0.87
    rued
    -0.79
    quickShipAvailable
    -0.76
    soDeliveryDate
    -0.73
    letters
    -0.73
    stakes
    -0.69
     Dragonbound
    -0.66
    frames
    -0.66
     Gazette
    -0.65
    taking
    -0.65
    POSITIVE LOGITS
     node
    1.42
     nodes
    1.29
    node
    0.88
     Node
    0.80
     guiActiveUn
    0.76
    Node
    0.75
     cluster
    0.75
     bottleneck
    0.75
     pier
    0.73
    js
    0.72
    Activations Density 0.007%

    No Known Activations