© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 12984
    Prev
    Next
    INDEX
    Explanations

    keywords related to events and event management

    oai_token-act-pair · gpt-3.5-turbo

    terms related to events and their categorization in a system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geon
    -0.71
    ACTED
    -0.71
    zzo
    -0.66
    zza
    -0.64
    Ô
    -0.63
    ately
    -0.62
    lems
    -0.62
     porous
    -0.62
    ghan
    -0.62
    aundering
    -0.62
    POSITIVE LOGITS
    uate
    0.90
    event
    0.86
    ually
    0.86
     events
    0.83
    Args
    0.83
     EVENT
    0.79
     event
    0.79
     Events
    0.79
     Event
    0.79
    uating
    0.78
    Activations Density 0.021%

    No Known Activations