© 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. 2-RES-JB
    11. 12592
    Prev
    Next
    INDEX
    Explanations

    mentions of drinks and cocktails

    oai_token-act-pair · gpt-3.5-turbo

    references to cocktails and mixed drinks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    66666666
    -0.80
     Parenthood
    -0.79
    founded
    -0.75
    debian
    -0.74
    ledged
    -0.74
    Merit
    -0.68
    orate
    -0.67
    shr
    -0.67
    thritis
    -0.67
    Ther
    -0.67
    POSITIVE LOGITS
     cocktail
    1.25
     cocktails
    1.05
     conco
    0.99
     waitress
    0.97
     drinks
    0.91
     drink
    0.83
     soda
    0.83
     lounge
    0.80
     latt
    0.80
     syrup
    0.79
    Activations Density 0.012%

    No Known Activations