© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 3898
    Prev
    Next
    INDEX
    Explanations

    items or concepts that can be used as specific functional items or building blocks

    oai_token-act-pair · gpt-3.5-turbo

    specific types of food and their associated uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    doms
    -0.91
    ichen
    -0.72
    kens
    -0.68
    lez
    -0.65
    olas
    -0.65
    ographies
    -0.64
     Tuc
    -0.62
    rants
    -0.60
    ymes
    -0.59
    azes
    -0.58
    POSITIVE LOGITS
     filler
    1.00
     deterrent
    0.99
     tool
    0.95
     accompan
    0.92
     reminder
    0.91
     substitute
    0.91
     replacement
    0.91
     centerpiece
    0.88
     basis
    0.87
     conduit
    0.86
    Activations Density 0.262%

    No Known Activations