© 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. 10-RES-JB
    11. 3079
    Prev
    Next
    INDEX
    Explanations

    references to the word "garb" or articles of clothing

    oai_token-act-pair · gpt-3.5-turbo

    references to events and gatherings, particularly those that involve costumes and celebratory themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    backer
    -0.70
    Maker
    -0.69
    beard
    -0.69
    hof
    -0.68
    auer
    -0.67
     Fargo
    -0.67
    zman
    -0.64
    aire
    -0.64
     depos
    -0.62
    OSE
    -0.62
    POSITIVE LOGITS
    ilion
    1.26
    illions
    1.01
    illion
    0.95
    cade
    0.93
    eteria
    0.92
    lov
    0.85
    ript
    0.83
    ilar
    0.80
    ages
    0.80
    ificial
    0.79
    Activations Density 0.049%

    No Known Activations