© 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. 20725
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming and technology, specifically in the context of commands and instructions

    oai_token-act-pair · gpt-3.5-turbo

    sentences indicating future actions or predictions

    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
     ANGEL
    -0.97
    isSpecialOrderable
    -0.87
    apesh
    -0.83
    igl
    -0.79
     Elise
    -0.78
    agn
    -0.77
     cane
    -0.77
    idel
    -0.76
    âĶĢ
    -0.75
    Carl
    -0.75
    POSITIVE LOGITS
     Post
    2.29
    Post
    2.18
    post
    2.12
     post
    1.99
     POST
    1.77
     posts
    1.54
    POST
    1.49
     Postal
    1.47
     Pre
    1.44
     postal
    1.38
    Activations Density 0.229%

    No Known Activations