© 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. 6-RES-JB
    11. 7567
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of beers

    oai_token-act-pair · gpt-3.5-turbo

    references to beer

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Telecommunications
    -0.87
     Telecom
    -0.80
    heed
    -0.71
     Lanka
    -0.71
    ortex
    -0.70
    itives
    -0.68
    inel
    -0.66
    aido
    -0.66
    UTC
    -0.65
    inosaur
    -0.64
    POSITIVE LOGITS
     brewed
    1.27
     drinkers
    1.06
     bottles
    0.90
     cans
    0.89
     brewing
    0.89
     tasting
    0.88
     bottle
    0.86
     drinking
    0.86
     brewer
    0.85
     lovers
    0.85
    Activations Density 0.030%

    No Known Activations