© 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. 18636
    Prev
    Next
    INDEX
    Explanations

    types of malt and hop flavors in beverages

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of beer and their characteristics, particularly focusing on hops and malt

    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
    NetMessage
    -0.82
    DragonMagazine
    -0.81
    LOS
    -0.74
     cler
    -0.73
    pmwiki
    -0.72
     guiActiveUn
    -0.72
     Robot
    -0.66
     Telecommunications
    -0.65
    vernment
    -0.65
     indemn
    -0.65
    POSITIVE LOGITS
     brewed
    1.13
     blends
    1.01
     whiskey
    0.96
     flavored
    0.95
     batches
    0.93
     bourbon
    0.92
     beers
    0.92
     flav
    0.91
     tasting
    0.90
     flavor
    0.90
    Activations Density 0.137%

    No Known Activations