© 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. 22132
    Prev
    Next
    INDEX
    Explanations

    mentions of editorial content

    oai_token-act-pair · gpt-3.5-turbo

    references to editorial content in various publications

    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
    chenko
    -0.75
    llan
    -0.73
    locked
    -0.72
    evil
    -0.71
    abouts
    -0.70
    aday
    -0.68
    anu
    -0.67
    agne
    -0.66
    duc
    -0.66
    phant
    -0.65
    POSITIVE LOGITS
    izing
    1.22
    ized
    1.17
    ising
    1.11
     board
    1.10
    IZE
    1.02
    izes
    1.02
     boards
    1.01
    ised
    1.00
     cartoons
    0.99
    ists
    0.96
    Activations Density 0.041%

    No Known Activations