© 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. 15
    Prev
    Next
    INDEX
    Explanations

    terms related to achievements or popularity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to media ratings and commercial success

    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
    actionDate
    -0.81
    ,,,,
    -0.81
    english
    -0.78
    Downloadha
    -0.75
     Edited
    -0.74
    ..................
    -0.72
    displayText
    -0.72
     Conditions
    -0.72
    .............
    -0.70
    uthor
    -0.68
    POSITIVE LOGITS
     darling
    1.44
     powerhouse
    1.41
     renaissance
    1.41
     jugg
    1.40
     frenzy
    1.38
     nightmare
    1.32
     onslaught
    1.30
     boom
    1.28
     paradise
    1.27
     resurgence
    1.25
    Activations Density 0.543%

    No Known Activations