© 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. 11-RES-JB
    11. 5035
    Prev
    Next
    INDEX
    Explanations

    words related to the act of selective picking or choosing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cherry-picking or selective sampling

    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
    olis
    -1.00
    icity
    -0.88
    ians
    -0.83
    ension
    -0.82
    ira
    -0.79
    iments
    -0.78
    eth
    -0.78
    aris
    -0.78
    enses
    -0.78
    inar
    -0.77
    POSITIVE LOGITS
     pie
    0.91
     gritty
    0.87
     goat
    0.86
     pick
    0.85
     grou
    0.83
     coaster
    0.81
     wagon
    0.80
     picking
    0.79
     fide
    0.79
     duck
    0.78
    Activations Density 0.206%

    No Known Activations