© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14770
    Prev
    Next
    INDEX
    Explanations

    words related to different types of whisk(e)y

    oai_token-act-pair · gpt-3.5-turbo

    references to types of alcoholic beverages, particularly whiskey and its variations

    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
    lez
    -0.76
    ULAR
    -0.74
    ularity
    -0.68
    nda
    -0.67
    rator
    -0.66
    ding
    -0.64
    TERN
    -0.64
     gears
    -0.64
    fter
    -0.63
    uders
    -0.63
    POSITIVE LOGITS
     whiskey
    1.37
     whisky
    1.26
     Whis
    1.16
     bourbon
    1.01
     whis
    1.00
    illery
    0.95
     rye
    0.92
     vodka
    0.90
     Scotch
    0.89
     tasting
    0.87
    Activations Density 0.019%

    No Known Activations