© 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. 9-RES-JB
    6. 3098
    Prev
    Next
    INDEX
    Explanations

    phrases related to computer programming and software development, specifically focusing on terms related to programming languages, libraries, and tools

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and names associated with programming and computer science

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cooke
    -0.70
     ÂŃ
    -0.65
     Volks
    -0.61
     MacArthur
    -0.60
     Townsend
    -0.60
     flattering
    -0.59
     Carroll
    -0.59
     Hasan
    -0.59
     headlined
    -0.59
     impart
    -0.58
    POSITIVE LOGITS
    Config
    1.08
    Browser
    1.04
    Debug
    1.02
    Proxy
    1.01
    SQL
    0.99
    Settings
    0.95
    Mode
    0.95
    Linux
    0.94
    Client
    0.94
    Shell
    0.93
    Activations Density 0.570%

    No Known Activations