© 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. 3-RES-JB
    11. 15554
    Prev
    Next
    INDEX
    Explanations

    specific mentions of types of beverages, mainly 'brews'

    oai_token-act-pair · gpt-3.5-turbo

    references to beer brewing

    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
    PsyNetMessage
    -0.73
     Vanguard
    -0.70
    Downloadha
    -0.70
    erved
    -0.69
     partName
    -0.67
     Camer
    -0.66
    ciating
    -0.65
     IMAGES
    -0.65
     Maurit
    -0.64
     Grizzlies
    -0.64
    POSITIVE LOGITS
     brewed
    1.19
     brew
    1.13
    eries
    1.04
    terness
    1.01
    masters
    1.00
     brewing
    0.99
    master
    0.99
     conco
    0.94
    brew
    0.91
    Brew
    0.87
    Activations Density 0.010%

    No Known Activations