© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 23865
    Prev
    Next
    INDEX
    Explanations

    phrases related to abstract concepts or ideas

    oai_token-act-pair · gpt-3.5-turbo

    concepts and phrases introduced by "the idea of."

    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
    keys
    -0.73
    WF
    -0.72
    iaries
    -0.70
    ients
    -0.69
    enth
    -0.68
    Sport
    -0.67
    WT
    -0.65
    burgh
    -0.63
    OGR
    -0.62
    far
    -0.62
    POSITIVE LOGITS
     owning
    1.00
     needing
    0.97
     creating
    0.95
     preserving
    0.94
     eliminating
    0.91
     having
    0.88
     arming
    0.88
     replacing
    0.88
     putting
    0.88
     combining
    0.87
    Activations Density 0.126%

    No Known Activations