© 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. 4-RES-JB
    11. 7559
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer programming and coding instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to programming concepts and file handling

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

    No Comments

    Negative Logits
    tumblr
    -0.65
    é¾įå
    -0.64
    ismo
    -0.63
    shaw
    -0.61
    mare
    -0.61
    ãĤ¤ãĥĪ
    -0.61
    spir
    -0.60
     Hobby
    -0.59
    âĢİ
    -0.59
    jam
    -0.58
    POSITIVE LOGITS
     specified
    1.01
     default
    0.95
     recursive
    0.94
     JSON
    0.94
     integer
    0.92
     output
    0.91
     numeric
    0.88
     UTF
    0.88
     socket
    0.87
     computed
    0.87
    Activations Density 0.820%

    No Known Activations