© 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. 1-RES-JB
    11. 20391
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "weird"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "weird" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptive
    -0.91
    ptives
    -0.83
    owder
    -0.82
    apers
    -0.80
    aders
    -0.78
    ailable
    -0.77
    ILA
    -0.76
    vation
    -0.74
    cussion
    -0.73
    utherford
    -0.73
    POSITIVE LOGITS
    ness
    1.00
    nesses
    0.95
     weird
    0.93
    ly
    0.87
     Weird
    0.87
    entimes
    0.86
     quirks
    0.85
     anomalies
    0.84
    ety
    0.82
    ishly
    0.79
    Activations Density 0.007%

    No Known Activations