© 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. 7-RES-JB
    11. 23131
    Prev
    Next
    INDEX
    Explanations

    phrases related to time periods when specific actions or events occur

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "during" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ettle
    -0.78
    ophe
    -0.74
    ledged
    -0.74
    esian
    -0.73
    ovan
    -0.73
    cloth
    -0.70
    DIV
    -0.69
    onica
    -0.68
    Added
    -0.66
    ards
    -0.64
    POSITIVE LOGITS
     periods
    1.05
     adolescence
    0.93
     wartime
    0.89
     daylight
    0.89
     infancy
    0.87
     renovations
    0.86
     halftime
    0.84
     emergencies
    0.82
     weekends
    0.78
     Ramadan
    0.78
    Activations Density 0.056%

    No Known Activations