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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 21170
    Prev
    Next
    INDEX
    Explanations

    actions or steps in a cooking recipe that involve a duration or a specific endpoint

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to cooking processes and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hack
    -0.71
    Rated
    -0.69
    netflix
    -0.64
    Gov
    -0.63
    Display
    -0.63
    Site
    -0.61
    Hunt
    -0.61
    deals
    -0.60
     Outs
    -0.59
    advertising
    -0.59
    POSITIVE LOGITS
     warmed
    0.96
     softened
    0.95
     aromatic
    0.90
     evenly
    0.88
     smooth
    0.88
     mixture
    0.87
     cooled
    0.87
    terness
    0.86
     moist
    0.86
     soaked
    0.85
    Activations Density 0.067%

    No Known Activations