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

    Neuronpedia

    Jacobian LensNEW
    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. 3330
    Prev
    Next
    INDEX
    Explanations

    phrases related to projects, events, and initiatives with specific names or titles

    oai_token-act-pair · gpt-3.5-turbo

    references to various programs, events, and initiatives

    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
     queen
    -0.79
     curs
    -0.71
     lowly
    -0.71
     havens
    -0.69
     recl
    -0.69
     elf
    -0.69
     elves
    -0.68
     communists
    -0.68
     knight
    -0.67
     unions
    -0.67
    POSITIVE LOGITS
     Facility
    1.31
    âĦ¢
    1.29
     Program
    1.24
     Initiative
    1.24
     Series
    1.23
     Programme
    1.23
     Fund
    1.19
     Collection
    1.16
     Agreement
    1.16
     Consortium
    1.13
    Activations Density 0.329%

    No Known Activations