© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 21051
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant or important events or entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "major" and its related contexts

    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
    mates
    -0.85
    mate
    -0.80
    mons
    -0.71
    opt
    -0.64
    ###
    -0.64
    rate
    -0.61
    ULTS
    -0.60
    aunting
    -0.60
    mong
    -0.60
     Thumbnails
    -0.60
    POSITIVE LOGITS
    itarian
    1.39
     depressive
    1.08
    itized
    0.94
     breakthrough
    0.92
     metropolitan
    0.87
     league
    0.86
     milestone
    0.85
     arteries
    0.84
    ities
    0.84
     milestones
    0.83
    Activations Density 0.047%

    No Known Activations