© 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. 8-RES-JB
    11. 17051
    Prev
    Next
    INDEX
    Explanations

    mentions of food and drink

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to food and cooking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whistlebl
    -0.85
     Trotsky
    -0.81
     Kissinger
    -0.79
     Lenin
    -0.77
     Reconstruction
    -0.77
     Democracy
    -0.77
     Chomsky
    -0.76
     Assange
    -0.76
     arbitration
    -0.74
     ideological
    -0.73
    POSITIVE LOGITS
     DIY
    1.04
     LOVE
    0.99
     veggies
    0.98
     ðŁĻĤ
    0.91
     ;)
    0.91
     crave
    0.90
     homemade
    0.89
    etsy
    0.88
     grandma
    0.88
     ðŁĺ
    0.88
    Activations Density 1.202%

    No Known Activations