© 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. 5791
    Prev
    Next
    INDEX
    Explanations

    specific events or gatherings related to various associations, conferences, and conventions

    oai_token-act-pair · gpt-3.5-turbo

    references to organizational meetings and events

    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
     porous
    -0.74
    etheless
    -0.73
     faulty
    -0.72
     ILCS
    -0.72
     trillions
    -0.66
     unintended
    -0.65
     pathways
    -0.63
     paths
    -0.63
    ahime
    -0.63
     unreliable
    -0.63
    POSITIVE LOGITS
     conference
    1.52
     seminar
    1.42
     summit
    1.39
    Fest
    1.37
     convention
    1.34
    conference
    1.32
     Summit
    1.31
     banquet
    1.29
     meeting
    1.29
     Meeting
    1.27
    Activations Density 0.391%

    No Known Activations