© 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 EvalsExportsinterp-engineNEWAPI 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. 11449
    Prev
    Next
    INDEX
    Explanations

    phrases related to interacting with and controlling digital content or tools

    oai_token-act-pair · gpt-3.5-turbo

    references to interactive features and functionalities in digital contexts

    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
    ©¶æ¥µ
    -0.79
    sted
    -0.74
    anism
    -0.73
    é¾
    -0.72
    forced
    -0.70
     Lau
    -0.69
     Beir
    -0.68
    Hart
    -0.66
     lawy
    -0.65
    first
    -0.64
    POSITIVE LOGITS
     automate
    1.22
     optimize
    1.20
     customize
    1.19
     manipulate
    1.12
     visualize
    1.11
     organize
    1.11
     simulate
    1.11
     navigate
    1.11
     improve
    1.11
     organise
    1.09
    Activations Density 0.283%

    No Known Activations