© 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. 3-RES-JB
    11. 15159
    Prev
    Next
    INDEX
    Explanations

    words related to activities or actions being performed over a period of time

    oai_token-act-pair · gpt-3.5-turbo

    the word "while" used in various contexts

    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
    aer
    -0.89
    elled
    -0.87
    hack
    -0.83
    oux
    -0.78
    orb
    -0.76
    Bas
    -0.75
    atter
    -0.75
    enter
    -0.75
    iosyncr
    -0.74
    inated
    -0.74
    POSITIVE LOGITS
     browsing
    1.02
     touring
    1.01
     researching
    0.98
     listening
    0.90
     maintaining
    0.89
     visiting
    0.89
     attending
    0.88
     watching
    0.87
     commuting
    0.87
     awaiting
    0.86
    Activations Density 0.061%

    No Known Activations