Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 22562
    Prev
    Next
    INDEX
    Explanations

    URL-like patterns within the text

    oai_token-act-pair · gpt-3.5-turbo

    comments or annotations related to code or scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĺħ
    -0.98
    phrine
    -0.83
    ylum
    -0.78
     livest
    -0.77
     subsequ
    -0.75
    xual
    -0.74
     confir
    -0.72
     strut
    -0.71
     tremend
    -0.71
     tsunami
    -0.70
    POSITIVE LOGITS
    ////////////////
    1.37
    ////////////////////////////////
    1.28
    ////////
    1.25
    ++++++++++++++++
    1.06
    ////
    1.01
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.90
    ================================================================
    0.85
    wcsstore
    0.84
    ãĤ§
    0.83
    ================================
    0.79
    Activations Density 0.014%

    No Known Activations