© 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. 6-RES-JB
    11. 13455
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to "Great" entities, such as "Great American", "Great White", and "Great Western"

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events and notable entities, particularly those related to American culture and history

    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
     guiActiveUn
    -0.64
    iard
    -0.63
    othal
    -0.61
    olutely
    -0.61
     clipboard
    -0.60
     Palest
    -0.59
    heid
    -0.59
    ascript
    -0.58
    ciating
    -0.58
    ilater
    -0.56
    POSITIVE LOGITS
    ghai
    0.70
    faith
    0.68
    great
    0.66
     awe
    0.65
    iuses
    0.65
    hra
    0.64
    intosh
    0.64
     Savings
    0.64
     Emin
    0.62
    iola
    0.61
    Activations Density 0.138%

    No Known Activations