© 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. 0-RES-JB
    11. 16349
    Prev
    Next
    INDEX
    Explanations

    phrases related to sitting in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "sit" and "lie" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rays
    -0.73
    ayer
    -0.73
     Reloaded
    -0.72
     giveaways
    -0.70
    orf
    -0.70
     bleach
    -0.69
     killer
    -0.69
     annotation
    -0.68
     emoji
    -0.68
     razor
    -0.67
    POSITIVE LOGITS
     Sit
    3.30
    Sit
    2.92
    sit
    2.49
     Lie
    1.58
     Situation
    1.30
     Chin
    1.30
     Sitting
    1.28
     Sop
    1.27
    Lie
    1.26
     Pend
    1.23
    Activations Density 0.057%

    No Known Activations