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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12326
    Prev
    Next
    INDEX
    Explanations

    phrases describing events or actions that happen over a period of time

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "During" and its frequency 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
     kind
    -0.78
     sort
    -0.78
     justice
    -0.70
     credibility
    -0.69
     default
    -0.68
     bold
    -0.67
     silly
    -0.66
     others
    -0.65
    rane
    -0.64
     too
    -0.64
    POSITIVE LOGITS
     During
    2.96
    During
    2.35
    during
    1.96
     Throughout
    1.89
     Afterwards
    1.89
     Shortly
    1.64
     Following
    1.56
     After
    1.55
     Initially
    1.54
     While
    1.54
    Activations Density 0.016%

    No Known Activations