© 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. 7-RES-JB
    6. 3780
    Prev
    Next
    INDEX
    Explanations

    hyperlinks within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to hyperlinks or links within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ynski
    -0.85
    Ħ¢
    -0.75
    otos
    -0.73
    sburg
    -0.73
     Pens
    -0.72
    issance
    -0.68
    ZI
    -0.66
    emale
    -0.66
    ¬¼
    -0.64
    brance
    -0.64
    POSITIVE LOGITS
    edin
    1.28
    later
    1.01
    link
    1.00
    ages
    0.98
     links
    0.94
    chain
    0.92
     link
    0.91
     linking
    0.84
    links
    0.80
     connecting
    0.79
    Activations Density 0.029%

    No Known Activations