© 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. 4-RES-JB
    11. 670
    Prev
    Next
    INDEX
    Explanations

    phrases or words indicating the potential occurrence of an event

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "event" and its contextual significance in various situations

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

    No Comments

    Negative Logits
    zie
    -0.73
    Rated
    -0.70
    reath
    -0.69
    ASHINGTON
    -0.63
     Views
    -0.63
    Stand
    -0.62
    âĵĺ
    -0.62
     Ammunition
    -0.60
    axter
    -0.59
    artisan
    -0.59
    POSITIVE LOGITS
    uate
    0.78
    ual
    0.76
     event
    0.75
     dstg
    0.71
    event
    0.70
    uating
    0.69
    ually
    0.67
     organisers
    0.67
    ĸļ
    0.66
     promoter
    0.64
    Activations Density 0.017%

    No Known Activations