© 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. 23231
    Prev
    Next
    INDEX
    Explanations

    event-related phrases and details

    oai_token-act-pair · gpt-3.5-turbo

    references to scheduled events and their characteristics

    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
     withholding
    -0.68
     Anon
    -0.65
     blocking
    -0.63
     controlling
    -0.62
     guessing
    -0.62
     liking
    -0.61
    Correct
    -0.60
     repairing
    -0.60
     Reduction
    -0.59
     storing
    -0.59
    POSITIVE LOGITS
     culmin
    1.27
     airs
    1.16
     aired
    1.13
     coincide
    1.10
     featured
    1.05
     attendees
    1.04
     lasted
    1.04
     occur
    1.03
     commence
    1.01
     kickoff
    0.98
    Activations Density 0.180%

    No Known Activations