© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9130
    Prev
    Next
    INDEX
    Explanations

    email addresses, Twitter handles, and website URLs

    oai_token-act-pair · gpt-3.5-turbo

    references to media outlets and social media platforms

    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
    ¶
    -0.68
     Takeru
    -0.64
     Mahjong
    -0.60
     Doodle
    -0.59
     surfing
    -0.58
     blush
    -0.57
     bump
    -0.56
     awa
    -0.55
    onga
    -0.55
     sneak
    -0.55
    POSITIVE LOGITS
    com
    1.36
    org
    1.12
    net
    1.05
    edu
    1.00
    wordpress
    0.99
    COM
    0.95
    tumblr
    0.94
    Com
    0.94
    blogspot
    0.92
    files
    0.90
    Activations Density 0.028%

    No Known Activations